Showing 1–50 of 61 results for author: Brintrup, A

Helicase: Uncertainty-Guided Supply Chain Knowledge Graph Construction with Autonomous Multi-Agent LLMs

Authors: Yunbo Long, Haolang Zhao, Ge Zheng, Alexandra Brintrup

Abstract: LLM-based multi-agent systems have been widely adopted for knowledge retrieval and report generation, synthesizing known information through web search and textual reasoning. However, many critical information tasks in supply chains are not simple one-shot queries: they are structural inference problems requiring multi-hop reasoning across complex, fragmented web resources. Questions such as \text… ▽ More LLM-based multi-agent systems have been widely adopted for knowledge retrieval and report generation, synthesizing known information through web search and textual reasoning. However, many critical information tasks in supply chains are not simple one-shot queries: they are structural inference problems requiring multi-hop reasoning across complex, fragmented web resources. Questions such as \textit{``Which Tesla components use lithium from Australian mines?''} have no answer in any single document; answers must be computationally synthesized through the autonomous construction and analysis of dynamic knowledge graphs assembled from fragmented, heterogeneous sources. Moreover, such discovery processes must be uncertainty-aware: decisions depend not only on answers but on calibrated confidence in their reliability, traceable to source quality and reasoning consistency. To address this capability gap, we propose \textit{Helicase}, an autonomous multi-agent LLM system for uncertainty-guided supply chain knowledge graph construction. \textit{Helicase} decomposes high-level supply-chain queries into executable investigation plans, coordinates specialized web-search, reasoning, and coding agents through iterative verification loops, and incrementally constructs query-specific supply chain knowledge graphs with per-fact uncertainty annotations. Its three-layer uncertainty framework tracks uncertainty at the action, trajectory, and memory layers, enabling both structural inference and calibrated confidence assessment. To evaluate autonomous reasoning across the full complexity spectrum, we introduce SCQA (Supply Chain Query Assessment), a benchmark of 80 supply chain queries organized into four quadrants spanning single-hop to multi-hop inference under both high and low data visibility. △ Less

Submitted 26 May, 2026; originally announced May 2026.

Generating Logically Consistent Synthetic Supply Chain Data with LLM-Driven Knowledge Graph Reasoning

Authors: Yunbo Long, Ge Zheng, Liming Xu, Alexandra Brintrup

Abstract: Synthetic data offers a promising solution to two persistent barriers in supply chain analytics: data scarcity and data privacy. However, for synthetic data to support operational simulation and decision-making, it must do more than reproduce the statistical distributions of real records, and also preserve the \emph{operational logic} that governs supply chain processes, including the temporal ord… ▽ More Synthetic data offers a promising solution to two persistent barriers in supply chain analytics: data scarcity and data privacy. However, for synthetic data to support operational simulation and decision-making, it must do more than reproduce the statistical distributions of real records, and also preserve the \emph{operational logic} that governs supply chain processes, including the temporal orderings, mathematical dependencies, hierarchical taxonomies, and conditional rules that make a record operationally plausible. We consider this logic as the ``physics'' of supply chain data. Existing tabular generative models are primarily optimized for distributional fidelity and downstream predictive utility, and therefore often generate records that appear statistically realistic but violate fundamental operational constraints. This paper introduces \textbf{\textit{TabKG}}, a knowledge-graph-guided framework for logically consistent synthetic supply chain tabular data generation. TabKG constructs a \textbf{\textit{Column Relationship Knowledge Graph (CR-KG)}} to represent data operational dependencies. It uses a multi-LLM ensemble with majority voting to propose candidate relationships from column metadata, validates these relationships against real data to remove hallucinated or unsupported edges, and then uses the validated CR-KG to guide generation. Specifically, TabKG compresses the original table into independent columns, generates these columns using a latent diffusion model, and deterministically reconstructs dependent columns according to the validated relationships, enforcing logical consistency by construction with respect to the discovered operational rules. △ Less

Submitted 26 May, 2026; originally announced May 2026.

EmoDistill: Offline Emotion Skill Distillation for Language Model Agents in Adversarial Negotiation

Authors: Yunbo Long, Haolang Zhao, Lukas Beckenbauer, Liming Xu, Alexandra Brintrup

Abstract: Post-trained LLMs are often optimized to align responses with human preferences, making them safe, polite, and conversationally appropriate. In adversarial negotiation, however, this alignment can become a vulnerability: emotionally framed language may steer agents toward the counterparty's interests. Using GoEmotions-based affective prompting, we show that emotion substantially shifts negotiation… ▽ More Post-trained LLMs are often optimized to align responses with human preferences, making them safe, polite, and conversationally appropriate. In adversarial negotiation, however, this alignment can become a vulnerability: emotionally framed language may steer agents toward the counterparty's interests. Using GoEmotions-based affective prompting, we show that emotion substantially shifts negotiation outcomes, suggesting that emotion is a strategic action channel rather than a surface style. Thus, we introduce \textbf{EmoDistill}, an offline framework for distilling emotional negotiation skills into language model agents. EmoDistill decomposes emotional strategy into emotion selection and emotion expression: an Implicit Q-Learning (IQL) selector learns \emph{which} emotion to express, while a Low-Rank Adaptation (LoRA)-based policy learns \emph{how} to express it through Supervised Fine-Tuning (SFT) and Judge Policy Optimization (JPO). Across four emotion-sensitive, high-stakes negotiation domains, SLM policies trained under the EmoDistill framework achieve the highest utility, outperforming vanilla SLM/LLM baselines and IQL-only emotion selection. Ablations show that emotion conditioning is essential, and transfer studies demonstrate generalization across domains, unseen counterparties, and trained-vs-trained tournaments. Overall, EmoDistill learns skills from offline agent-to-agent interactions, avoiding costly online negotiation during training. △ Less

Submitted 26 May, 2026; originally announced May 2026.

VeriTrace: Evolving Mental Models for Deep Research Agents

Authors: Haolang Zhao, Yunbo Long, Lukas Beckenbauer, Alexandra Brintrup

Abstract: Deep research agents face vast, interdependent, and pervasively uncertain information. Existing systems explore what evolving intermediate representations should look like, but leave their evolution to the LLM's implicit reasoning. Without explicit regulation, the intermediate layer is easily contaminated by mixed-quality information and propagates errors along its dependencies, so model scale oft… ▽ More Deep research agents face vast, interdependent, and pervasively uncertain information. Existing systems explore what evolving intermediate representations should look like, but leave their evolution to the LLM's implicit reasoning. Without explicit regulation, the intermediate layer is easily contaminated by mixed-quality information and propagates errors along its dependencies, so model scale often ends up substituting for absent regulation. We argue that an agent's mental model should instead evolve through explicit feedback that continuously aligns task understanding with reality, and identify three regulatory loops: interpretive update, deviation feedback, and schema revision. We realise this in VeriTrace, a cognitive-graph framework that explicitly implements the three loops. Using matched Qwen3.5-27B backbones, VeriTrace improves over the strongest matched baseline by 4.22 pp on DeepResearch Bench (DRB) Insight (1.49 pp Overall) and by 5.9 pp Overall win rate on DeepConsult. With Config-DeepSeek, it achieves the strongest reproducible open-source result on DRB. △ Less

Submitted 25 May, 2026; originally announced May 2026.

Self-Improving Tabular Language Models via Iterative Reward-Guided Post-Training

Authors: Yunbo Long, Tejumade Afonja, Guangya Hao, Alexandra Brintrup, Mario Fritz

Abstract: Tabular language models can generate synthetic tables by modeling rows as token sequences, but they are typically trained once with supervised fine-tuning and then used as static synthesizers. This is limiting because next-token likelihood does not directly optimize the distributional, utility, and indistinguishability properties used to evaluate synthetic data. We study iterative reward-guided po… ▽ More Tabular language models can generate synthetic tables by modeling rows as token sequences, but they are typically trained once with supervised fine-tuning and then used as static synthesizers. This is limiting because next-token likelihood does not directly optimize the distributional, utility, and indistinguishability properties used to evaluate synthetic data. We study iterative reward-guided post-training for tabular language models through a generate--score--align protocol, where a generator samples synthetic rows, a task-specified reward ranks them, and the model is updated relative to a fixed supervised reference. Within this protocol, we propose \textbf{TabGRAA} (\textbf{Tab}ular \textbf{G}roup-\textbf{R}elative \textbf{A}dvantage \textbf{A}lignment), a group-relative alignment method that compares high- and low-reward generated groups using group-averaged policy/reference log-ratios rather than one-to-one preference pairs. Across five mixed-type benchmarks, TabGRAA improves a GReaT backbone beyond additional supervised fine-tuning and achieves the strongest average trade-off among adapted DPO, KTO, and NPO baselines on fidelity and downstream utility, while maintaining empirical privacy diagnostics near the supervised baseline. Ablations show that the gains depend on meaningful reward ranking and stable group-level updates rather than extra training alone. Reward-substitution and scorer-separation studies further show that the post-training loop can use both classifier-based and classifier-free rewards, and that proper scorer separation is important for preserving the fidelity--utility--privacy trade-off. These results position TabGRAA as a self-improving post-training method for tabular language-model generators, complementary to strong static tabular synthesizers. △ Less

Submitted 17 May, 2026; v1 submitted 20 April, 2026; originally announced April 2026.

Structural Consequences of Policy-Based Interventions on the Global Supply Chain Network

Authors: Lea Karbevska, Liming Xu, Zehui Dai, Sara AlMahri, Alexandra Brintrup

Abstract: As global political tensions rise and the anticipation of additional tariffs from the United States on international trade increases, the issues of economic independence and supply chain resilience become more prominent. The importance of supply chain resilience has been further underscored by disruptions caused by the COVID-19 pandemic and the ongoing war in Ukraine. In light of these challenges,… ▽ More As global political tensions rise and the anticipation of additional tariffs from the United States on international trade increases, the issues of economic independence and supply chain resilience become more prominent. The importance of supply chain resilience has been further underscored by disruptions caused by the COVID-19 pandemic and the ongoing war in Ukraine. In light of these challenges, ranging from geopolitical instability to product supply uncertainties, governments are increasingly focused on adopting new trade policies. This study explores the impact of several of these policies on the global electric vehicle (EV) supply chain network, with a particular focus on their effects on country clusters and the broader structure of international trade. Specifically, we analyse three key policies: Country Plus One, Friendshoring, and Reshoring. Our findings show that Friendshoring, contrary to expectations, leads to greater globalisation by increasing the number of supply links across friendly countries, potentially raising transaction costs. The Country Plus One policy similarly enhances network density through redundant links, while the Reshoring policy creates challenges in the EV sector due to the high number of irreplaceable products. Additionally, the effects of these policies vary across industries; for instance, mining goods being less affected in Country Plus One than the Friendshoring policy. △ Less

Submitted 14 April, 2026; v1 submitted 13 April, 2026; originally announced April 2026.

Modelling viable supply networks with cooperative adaptive financing

Authors: Yaniv Proselkov, Liming Xu, Alexandra Brintrup

Abstract: We propose a financial liquidity policy sharing method for firm-to-firm supply networks, introducing a scalable autonomous control function for viable complex adaptive supply networks. Cooperation and competition in supply chains is reconciled through overlapping collaborative sets, making firms interdependent and enabling distributed risk governance. How cooperative range - visibility - affects v… ▽ More We propose a financial liquidity policy sharing method for firm-to-firm supply networks, introducing a scalable autonomous control function for viable complex adaptive supply networks. Cooperation and competition in supply chains is reconciled through overlapping collaborative sets, making firms interdependent and enabling distributed risk governance. How cooperative range - visibility - affects viability is studied using dynamic complex adaptive systems modelling. We find that viability needs cooperation; visibility and viability grow together in scale-free supply networks; and distributed control, where firms only have limited partner information, outperforms centralised control. This suggests that policy toward network viability should implement distributed supply chain financial governance, supporting interfirm collaboration, to enable autonomous control. △ Less

Submitted 19 January, 2026; originally announced January 2026.

MSC Class: 90B15 (Primary) 90B06; 05C82; 91B69; 68M14; 91G45; 93A16 (Secondary) ACM Class: I.2.11; I.6.8; G.2.2; C.2.4

Automating Supply Chain Disruption Monitoring via an Agentic AI Approach

Authors: Sara AlMahri, Liming Xu, Alexandra Brintrup

Abstract: Modern supply chains are increasingly exposed to disruptions from geopolitical events, demand shocks, trade restrictions, to natural disasters. While many of these disruptions originate deep in the supply network, most companies still lack visibility beyond Tier-1 suppliers, leaving upstream vulnerabilities undetected until the impact cascades downstream. To overcome this blind-spot and move from… ▽ More Modern supply chains are increasingly exposed to disruptions from geopolitical events, demand shocks, trade restrictions, to natural disasters. While many of these disruptions originate deep in the supply network, most companies still lack visibility beyond Tier-1 suppliers, leaving upstream vulnerabilities undetected until the impact cascades downstream. To overcome this blind-spot and move from reactive recovery to proactive resilience, we introduce a minimally supervised agentic AI framework that autonomously monitors, analyses, and responds to disruptions across extended supply networks. The architecture comprises seven specialised agents powered by large language models and deterministic tools that jointly detect disruption signals from unstructured news, map them to multi-tier supplier networks, evaluate exposure based on network structure, and recommend mitigations such as alternative sourcing options. \rev{We evaluate the framework across 30 synthesised scenarios covering three automotive manufacturers and five disruption classes. The system achieves high accuracy across core tasks, with F1 scores between 0.962 and 0.991, and performs full end-to-end analyses in a mean of 3.83 minutes at a cost of \$0.0836 per disruption. Relative to industry benchmarks of multi-day, analyst-driven assessments, this represents a reduction of more than three orders of magnitude in response time. A real-world case study of the 2022 Russia-Ukraine conflict further demonstrates operational applicability. This work establishes a foundational step toward building resilient, proactive, and autonomous supply chains capable of managing disruptions across deep-tier networks. △ Less

Submitted 14 January, 2026; originally announced January 2026.

Topological Federated Clustering via Gravitational Potential Fields under Local Differential Privacy

Authors: Yunbo Long, Jiaquan Zhang, Xi Chen, Alexandra Brintrup

Abstract: Clustering non-independent and identically distributed (non-IID) data under local differential privacy (LDP) in federated settings presents a critical challenge: preserving privacy while maintaining accuracy without iterative communication. Existing one-shot methods rely on unstable pairwise centroid distances or neighborhood rankings, degrading severely under strong LDP noise and data heterogenei… ▽ More Clustering non-independent and identically distributed (non-IID) data under local differential privacy (LDP) in federated settings presents a critical challenge: preserving privacy while maintaining accuracy without iterative communication. Existing one-shot methods rely on unstable pairwise centroid distances or neighborhood rankings, degrading severely under strong LDP noise and data heterogeneity. We present Gravitational Federated Clustering (GFC), a novel approach to privacy-preserving federated clustering that overcomes the limitations of distance-based methods under varying LDP. Addressing the critical challenge of clustering non-IID data with diverse privacy guarantees, GFC transforms privatized client centroids into a global gravitational potential field where true cluster centers emerge as topologically persistent singularities. Our framework introduces two key innovations: (1) a client-side compactness-aware perturbation mechanism that encodes local cluster geometry as "mass" values, and (2) a server-side topological aggregation phase that extracts stable centroids through persistent homology analysis of the potential field's superlevel sets. Theoretically, we establish a closed-form bound between the privacy budget $ε$ and centroid estimation error, proving the potential field's Lipschitz smoothing properties exponentially suppress noise in high-density regions. Empirically, GFC outperforms state-of-the-art methods on ten benchmarks, especially under strong LDP constraints ($ε< 1$), while maintaining comparable performance at lower privacy budgets. By reformulating federated clustering as a topological persistence problem in a synthetic physics-inspired space, GFC achieves unprecedented privacy-accuracy trade-offs without iterative communication, providing a new perspective for privacy-preserving distributed learning. △ Less

Submitted 30 November, 2025; originally announced December 2025.

EQ-Negotiator: Dynamic Emotional Personas Empower Small Language Models for Edge-Deployable Credit Negotiation

Authors: Yunbo Long, Yuhan Liu, Alexandra Brintrup

Abstract: The deployment of large language models (LLMs) in automated negotiation has set a high performance benchmark, but their computational cost and data privacy requirements render them unsuitable for many privacy-sensitive, on-device applications such as mobile assistants, embodied AI agents or private client interactions. While small language models (SLMs) offer a practical alternative, they suffer f… ▽ More The deployment of large language models (LLMs) in automated negotiation has set a high performance benchmark, but their computational cost and data privacy requirements render them unsuitable for many privacy-sensitive, on-device applications such as mobile assistants, embodied AI agents or private client interactions. While small language models (SLMs) offer a practical alternative, they suffer from a significant performance gap compared to LLMs in playing emotionally charged complex personas, especially for credit negotiation. This paper introduces EQ-Negotiator, a novel framework that bridges this capability gap using emotional personas. Its core is a reasoning system that integrates game theory with a Hidden Markov Model(HMM) to learn and track debtor emotional states online, without pre-training. This allows EQ-Negotiator to equip SLMs with the strategic intelligence to counter manipulation while de-escalating conflict and upholding ethical standards. Through extensive agent-to-agent simulations across diverse credit negotiation scenarios, including adversarial debtor strategies like cheating, threatening, and playing the victim, we show that a 7B parameter language model with EQ-Negotiator achieves better debt recovery and negotiation efficiency than baseline LLMs more than 10 times its size. This work advances persona modeling from descriptive character profiles to dynamic emotional architectures that operate within privacy constraints. Besides, this paper establishes that strategic emotional intelligence, not raw model scale, is the critical factor for success in automated negotiation, paving the way for effective, ethical, and privacy-preserving AI negotiators that can operate on the edge. △ Less

Submitted 25 March, 2026; v1 submitted 5 November, 2025; originally announced November 2025.

Orchestrator: Active Inference for Multi-Agent Systems in Long-Horizon Tasks

Authors: Lukas Beckenbauer, Johannes-Lucas Loewe, Ge Zheng, Alexandra Brintrup

Abstract: Complex, non-linear tasks challenge LLM-enhanced multi-agent systems (MAS) due to partial observability and suboptimal coordination. We propose Orchestrator, a novel MAS framework that leverages attention-inspired self-emergent coordination and reflective benchmarking to optimize global task performance. Orchestrator introduces a monitoring mechanism to track agent-environment dynamics, using acti… ▽ More Complex, non-linear tasks challenge LLM-enhanced multi-agent systems (MAS) due to partial observability and suboptimal coordination. We propose Orchestrator, a novel MAS framework that leverages attention-inspired self-emergent coordination and reflective benchmarking to optimize global task performance. Orchestrator introduces a monitoring mechanism to track agent-environment dynamics, using active inference benchmarks to optimize system behavior. By tracking agent-to-agent and agent-to-environment interaction, Orchestrator mitigates the effects of partial observability and enables agents to approximate global task solutions more efficiently. We evaluate the framework on a series of maze puzzles of increasing complexity, demonstrating its effectiveness in enhancing coordination and performance in dynamic, non-linear environments with long-horizon objectives. △ Less

Submitted 6 September, 2025; originally announced September 2025.

SynDelay: A Synthetic Dataset for Delivery Delay Prediction

Authors: Liming Xu, Yunbo Long, Alexandra Brintrup

Abstract: Artificial intelligence (AI) is transforming supply chain management, yet progress in predictive tasks -- such as delivery delay prediction -- remains constrained by the scarcity of high-quality, openly available datasets. Existing datasets are often proprietary, small, or inconsistently maintained, hindering reproducibility and benchmarking. We present SynDelay, a synthetic dataset designed for d… ▽ More Artificial intelligence (AI) is transforming supply chain management, yet progress in predictive tasks -- such as delivery delay prediction -- remains constrained by the scarcity of high-quality, openly available datasets. Existing datasets are often proprietary, small, or inconsistently maintained, hindering reproducibility and benchmarking. We present SynDelay, a synthetic dataset designed for delivery delay prediction. Generated using an advanced generative model trained on real-world data, SynDelay preserves realistic delivery patterns while ensuring privacy. Although not entirely free of noise or inconsistencies, it provides a challenging and practical testbed for advancing predictive modelling. To support adoption, we provide baseline results and evaluation metrics as initial benchmarks, serving as reference points rather than state-of-the-art claims. SynDelay is publicly available through the Supply Chain Data Hub, an open initiative promoting dataset sharing and benchmarking in supply chain AI. We encourage the community to contribute datasets, models, and evaluation practices to advance research in this area. All code is openly accessible at https://supplychaindatahub.org. △ Less

Submitted 30 August, 2025; originally announced September 2025.

Comments: This paper incldues 1 figure and 2 tables

EvoEmo: Towards Evolved Emotional Policies for Adversarial LLM Agents in Multi-Turn Price Negotiation

Authors: Yunbo Long, Liming Xu, Lukas Beckenbauer, Yuhan Liu, Alexandra Brintrup

Abstract: Recent research on Chain-of-Thought (CoT) reasoning in Large Language Models (LLMs) has demonstrated that agents can engage in \textit{complex}, \textit{multi-turn} negotiations, opening new avenues for agentic AI. However, existing LLM agents largely overlook the functional role of emotions in such negotiations, instead generating passive, preference-driven emotional responses that make them vuln… ▽ More Recent research on Chain-of-Thought (CoT) reasoning in Large Language Models (LLMs) has demonstrated that agents can engage in \textit{complex}, \textit{multi-turn} negotiations, opening new avenues for agentic AI. However, existing LLM agents largely overlook the functional role of emotions in such negotiations, instead generating passive, preference-driven emotional responses that make them vulnerable to manipulation and strategic exploitation by adversarial counterparts. To address this gap, we present EvoEmo, an evolutionary reinforcement learning framework that optimizes dynamic emotional expression in negotiations. EvoEmo models emotional state transitions as a Markov Decision Process and employs population-based genetic optimization to evolve high-reward emotion policies across diverse negotiation scenarios. We further propose an evaluation framework with two baselines -- vanilla strategies and fixed-emotion strategies -- for benchmarking emotion-aware negotiation. Extensive experiments and ablation studies show that EvoEmo consistently outperforms both baselines, achieving higher success rates, higher efficiency, and increased buyer savings. This findings highlight the importance of adaptive emotional expression in enabling more effective LLM agents for multi-turn negotiation. The code is available at \href{https://github.com/Yunbo-max/EvoEmo}{\textcolor{red}{https://github.com/Yunbo-max/EvoEmo}}. △ Less

Submitted 26 May, 2026; v1 submitted 4 September, 2025; originally announced September 2025.

Redirection for Erasing Memory (REM): Towards a universal unlearning method for corrupted data

Authors: Stefan Schoepf, Michael Curtis Mozer, Nicole Elyse Mitchell, Alexandra Brintrup, Georgios Kaissis, Peter Kairouz, Eleni Triantafillou

Abstract: Machine unlearning is studied for a multitude of tasks, but specialization of unlearning methods to particular tasks has made their systematic comparison challenging. To address this issue, we propose a conceptual space to characterize diverse corrupted data unlearning tasks in vision classifiers. This space is described by two dimensions, the discovery rate (the fraction of the corrupted data tha… ▽ More Machine unlearning is studied for a multitude of tasks, but specialization of unlearning methods to particular tasks has made their systematic comparison challenging. To address this issue, we propose a conceptual space to characterize diverse corrupted data unlearning tasks in vision classifiers. This space is described by two dimensions, the discovery rate (the fraction of the corrupted data that are known at unlearning time) and the statistical regularity of the corrupted data (from random exemplars to shared concepts). Methods proposed previously have been targeted at portions of this space and-we show-fail predictably outside these regions. We propose a novel method, Redirection for Erasing Memory (REM), whose key feature is that corrupted data are redirected to dedicated neurons introduced at unlearning time and then discarded or deactivated to suppress the influence of corrupted data. REM performs strongly across the space of tasks, in contrast to prior SOTA methods that fail outside the regions for which they were designed. △ Less

Submitted 3 February, 2026; v1 submitted 23 May, 2025; originally announced May 2025.

Comments: Accepted as a main track paper at ICLR 2026 https://openreview.net/forum?id=xG0mQ4Xsfm

EmoDebt: Bayesian-Optimized Emotional Intelligence for Strategic Agent-to-Agent Debt Recovery

Authors: Yunbo Long, Yuhan Liu, Liming Xu, Alexandra Brintrup

Abstract: The emergence of autonomous Large Language Model (LLM) agents has created a new ecosystem of strategic, agent-to-agent interactions. However, a critical challenge remains unaddressed: in high-stakes, emotion-sensitive domains like debt collection, LLM agents pre-trained on human dialogue are vulnerable to exploitation by adversarial counterparts who simulate negative emotions to derail negotiation… ▽ More The emergence of autonomous Large Language Model (LLM) agents has created a new ecosystem of strategic, agent-to-agent interactions. However, a critical challenge remains unaddressed: in high-stakes, emotion-sensitive domains like debt collection, LLM agents pre-trained on human dialogue are vulnerable to exploitation by adversarial counterparts who simulate negative emotions to derail negotiations. To fill this gap, we first contribute a novel dataset of simulated debt recovery scenarios and a multi-agent simulation framework. Within this framework, we introduce EmoDebt, an LLM agent architected for robust performance. Its core innovation is a Bayesian-optimized emotional intelligence engine that reframes a model's ability to express emotion in negotiation as a sequential decision-making problem. Through online learning, this engine continuously tunes EmoDebt's emotional transition policies, discovering optimal counter-strategies against specific debtor tactics. Extensive experiments on our proposed benchmark demonstrate that EmoDebt achieves significant strategic robustness, substantially outperforming non-adaptive and emotion-agnostic baselines across key performance metrics, including success rate and operational efficiency. By introducing both a critical benchmark and a robustly adaptive agent, this work establishes a new foundation for deploying strategically robust LLM agents in adversarial, emotion-sensitive debt interactions. The code is available at \textcolor{blue}{https://github.com/Yunbo-max/EmoDebt}. △ Less

Submitted 3 November, 2025; v1 submitted 26 March, 2025; originally announced March 2025.

TuneNSearch: a hybrid transfer learning and local search approach for solving vehicle routing problems

Authors: Arthur Corrêa, Cristóvão Silva, Liming Xu, Alexandra Brintrup, Samuel Moniz

Abstract: This paper introduces TuneNSearch, a hybrid transfer learning and local search approach for addressing diverse variants of the vehicle routing problem (VRP). Our method uses reinforcement learning to generate high-quality solutions, which are subsequently refined by an efficient local search procedure. To ensure broad adaptability across VRP variants, TuneNSearch begins with a pre-training phase o… ▽ More This paper introduces TuneNSearch, a hybrid transfer learning and local search approach for addressing diverse variants of the vehicle routing problem (VRP). Our method uses reinforcement learning to generate high-quality solutions, which are subsequently refined by an efficient local search procedure. To ensure broad adaptability across VRP variants, TuneNSearch begins with a pre-training phase on the multi-depot VRP (MDVRP), followed by a fine-tuning phase to adapt it to other problem formulations. The learning phase utilizes a Transformer-based architecture enhanced with edge-aware attention, which integrates edge distances directly into the attention mechanism to better capture spatial relationships inherent to routing problems. We show that the pre-trained model generalizes effectively to single-depot variants, achieving performance comparable to models trained specifically on single-depot instances. Simultaneously, it maintains strong performance on multi-depot variants, an ability that models pre-trained solely on single-depot problems lack. For example, on 100-node instances of multi-depot variants, TuneNSearch outperforms a model pre-trained on the CVRP by 44%. In contrast, on 100-node instances of single-depot variants, TuneNSearch performs similar to the CVRP model. To validate the effectiveness of our method, we conduct extensive computational experiments on public benchmark and randomly generated instances. Across multiple CVRPLIB datasets, TuneNSearch consistently achieves performance deviations of less than 3% from the best-known solutions in the literature, compared to 6-25% for other neural-based models, depending on problem complexity. Overall, our approach demonstrates strong generalization to different problem sizes, instance distributions, and VRP formulations, while maintaining polynomial runtime complexity despite the integration of the local search algorithm. △ Less

Submitted 29 October, 2025; v1 submitted 16 March, 2025; originally announced March 2025.

Journal ref: Computers & Operations Research, 2026, 107433

PA-CFL: Privacy-Adaptive Clustered Federated Learning for Transformer-Based Sales Forecasting on Heterogeneous Retail Data

Authors: Yunbo Long, Liming Xu, Ge Zheng, Alexandra Brintrup

Abstract: Federated learning (FL) enables retailers to share model parameters for demand forecasting while maintaining privacy. However, heterogeneous data across diverse regions, driven by factors such as varying consumer behavior, poses challenges to the effectiveness of federated learning. To tackle this challenge, we propose Privacy-Adaptive Clustered Federated Learning (PA-CFL) tailored for demand fore… ▽ More Federated learning (FL) enables retailers to share model parameters for demand forecasting while maintaining privacy. However, heterogeneous data across diverse regions, driven by factors such as varying consumer behavior, poses challenges to the effectiveness of federated learning. To tackle this challenge, we propose Privacy-Adaptive Clustered Federated Learning (PA-CFL) tailored for demand forecasting on heterogeneous retail data. By leveraging differential privacy and feature importance distribution, PA-CFL groups retailers into distinct ``bubbles'', each forming its own federated learning system to effectively isolate data heterogeneity. Within each bubble, Transformer models are designed to predict local sales for each client. Our experiments demonstrate that PA-CFL significantly surpasses FedAvg and outperforms local learning in demand forecasting performance across all participating clients. Compared to local learning, PA-CFL achieves a 5.4% improvement in R^2, a 69% reduction in RMSE, and a 45% decrease in MAE. Our approach enables effective FL through adaptive adjustments to diverse noise levels and the range of clients participating in each bubble. By grouping participants and proactively filtering out high-risk clients, PA-CFL mitigates potential threats to the FL system. The findings demonstrate PA-CFL's ability to enhance federated learning in time series prediction tasks with heterogeneous data, achieving a balance between forecasting accuracy and privacy preservation in retail applications. Additionally, PA-CFL's capability to detect and neutralize poisoned data from clients enhances the system's robustness and reliability. △ Less

Submitted 21 March, 2025; v1 submitted 15 March, 2025; originally announced March 2025.

Efficient and Privacy-Preserved Link Prediction via Condensed Graphs

Authors: Yunbo Long, Liming Xu, Alexandra Brintrup

Abstract: Link prediction is crucial for uncovering hidden connections within complex networks, enabling applications such as identifying potential customers and products. However, this research faces significant challenges, including concerns about data privacy, as well as high computational and storage costs, especially when dealing with large-scale networks. Condensed graphs, which are much smaller than… ▽ More Link prediction is crucial for uncovering hidden connections within complex networks, enabling applications such as identifying potential customers and products. However, this research faces significant challenges, including concerns about data privacy, as well as high computational and storage costs, especially when dealing with large-scale networks. Condensed graphs, which are much smaller than the original graphs while retaining essential information, has become an effective solution to both maintain data utility and preserve privacy. Existing methods, however, initialize synthetic graphs through random node selection without considering node connectivity, and are mainly designed for node classification tasks. As a result, their potential for privacy-preserving link prediction remains largely unexplored. We introduce HyDRO\textsuperscript{+}, a graph condensation method guided by algebraic Jaccard similarity, which leverages local connectivity information to optimize condensed graph structures. Extensive experiments on four real-world networks show that our method outperforms state-of-the-art methods and even the original networks in balancing link prediction accuracy and privacy preservation. Moreover, our method achieves nearly 20* faster training and reduces storage requirements by 452*, as demonstrated on the Computers dataset, compared to link prediction on the original networks. This work represents the first attempt to leverage condensed graphs for privacy-preserving link prediction information sharing in real-world complex networks. It offers a promising pathway for preserving link prediction information while safeguarding privacy, advancing the use of graph condensation in large-scale networks with privacy concerns. △ Less

Submitted 15 March, 2025; originally announced March 2025.

An Analytics-Driven Approach to Enhancing Supply Chain Visibility with Graph Neural Networks and Federated Learning

Authors: Ge Zheng, Alexandra Brintrup

Abstract: In today's globalised trade, supply chains form complex networks spanning multiple organisations and even countries, making them highly vulnerable to disruptions. These vulnerabilities, highlighted by recent global crises, underscore the urgent need for improved visibility and resilience of the supply chain. However, data-sharing limitations often hinder the achievement of comprehensive visibility… ▽ More In today's globalised trade, supply chains form complex networks spanning multiple organisations and even countries, making them highly vulnerable to disruptions. These vulnerabilities, highlighted by recent global crises, underscore the urgent need for improved visibility and resilience of the supply chain. However, data-sharing limitations often hinder the achievement of comprehensive visibility between organisations or countries due to privacy, security, and regulatory concerns. Moreover, most existing research studies focused on individual firm- or product-level networks, overlooking the multifaceted interactions among diverse entities that characterise real-world supply chains, thus limiting a holistic understanding of supply chain dynamics. To address these challenges, we propose a novel approach that integrates Federated Learning (FL) and Graph Convolutional Neural Networks (GCNs) to enhance supply chain visibility through relationship prediction in supply chain knowledge graphs. FL enables collaborative model training across countries by facilitating information sharing without requiring raw data exchange, ensuring compliance with privacy regulations and maintaining data security. GCNs empower the framework to capture intricate relational patterns within knowledge graphs, enabling accurate link prediction to uncover hidden connections and provide comprehensive insights into supply chain networks. Experimental results validate the effectiveness of the proposed approach, demonstrating its ability to accurately predict relationships within country-level supply chain knowledge graphs. This enhanced visibility supports actionable insights, facilitates proactive risk management, and contributes to the development of resilient and adaptive supply chain strategies, ensuring that supply chains are better equipped to navigate the complexities of the global economy. △ Less

Submitted 10 March, 2025; originally announced March 2025.

Comments: 15 pages, 5 figures, 5 tables, submitted to a journal

LLM-TabLogic: Preserving Inter-Column Logical Relationships in Synthetic Tabular Data via Prompt-Guided Latent Diffusion

Authors: Yunbo Long, Liming Xu, Alexandra Brintrup

Abstract: Synthetic tabular data are increasingly being used to replace real data, serving as an effective solution that simultaneously protects privacy and addresses data scarcity. However, in addition to preserving global statistical properties, synthetic datasets must also maintain domain-specific logical consistency**-**especially in complex systems like supply chains, where fields such as shipment date… ▽ More Synthetic tabular data are increasingly being used to replace real data, serving as an effective solution that simultaneously protects privacy and addresses data scarcity. However, in addition to preserving global statistical properties, synthetic datasets must also maintain domain-specific logical consistency**-**especially in complex systems like supply chains, where fields such as shipment dates, locations, and product categories must remain logically consistent for real-world usability. Existing generative models often overlook these inter-column relationships, leading to unreliable synthetic tabular data in real-world applications. To address these challenges, we propose LLM-TabLogic, a novel approach that leverages Large Language Model reasoning to capture and compress the complex logical relationships among tabular columns, while these conditional constraints are passed into a Score-based Diffusion model for data generation in latent space. Through extensive experiments on real-world industrial datasets, we evaluate LLM-TabLogic for column reasoning and data generation, comparing it with five baselines including SMOTE and state-of-the-art generative models. Our results show that LLM-TabLogic demonstrates strong generalization in logical inference, achieving over 90% accuracy on unseen tables. Furthermore, our method outperforms all baselines in data generation by fully preserving inter-column relationships while maintaining the best balance between data fidelity, utility, and privacy. This study presents the first method to effectively preserve inter-column relationships in synthetic tabular data generation without requiring domain knowledge, offering new insights for creating logically consistent real-world tabular data. The code is available at https://github.com/Yunbo-max/TabKG. △ Less

Submitted 17 May, 2026; v1 submitted 3 March, 2025; originally announced March 2025.

Evaluating Inter-Column Logical Relationships in Synthetic Tabular Data Generation

Authors: Yunbo Long, Liming Xu, Alexandra Brintrup

Abstract: Current evaluations of synthetic tabular data mainly focus on how well joint distributions are modeled, often overlooking the assessment of their effectiveness in preserving realistic event sequences and coherent entity relationships across columns.This paper proposes three evaluation metrics designed to assess the preservation of logical relationships among columns in synthetic tabular data. We v… ▽ More Current evaluations of synthetic tabular data mainly focus on how well joint distributions are modeled, often overlooking the assessment of their effectiveness in preserving realistic event sequences and coherent entity relationships across columns.This paper proposes three evaluation metrics designed to assess the preservation of logical relationships among columns in synthetic tabular data. We validate these metrics by assessing the performance of both classical and state-of-the-art generation methods on a real-world industrial dataset.Experimental results reveal that existing methods often fail to rigorously maintain logical consistency (e.g., hierarchical relationships in geography or organization) and dependencies (e.g., temporal sequences or mathematical relationships), which are crucial for preserving the fine-grained realism of real-world tabular data. Building on these insights, this study also discusses possible pathways to better capture logical relationships while modeling the distribution of synthetic tabular data. The code is available at https://github.com/Yunbo-max/TabLogicEval. △ Less

Submitted 17 May, 2026; v1 submitted 6 February, 2025; originally announced February 2025.

Random Walk Guided Hyperbolic Graph Distillation

Authors: Yunbo Long, Liming Xu, Stefan Schoepf, Alexandra Brintrup

Abstract: Graph distillation (GD) is an effective approach to extract useful information from large-scale network structures. However, existing methods, which operate in Euclidean space to generate condensed graphs, struggle to capture the inherent tree-like geometry of real-world networks, resulting in distilled graphs with limited task-specific information for downstream tasks. Furthermore, these methods… ▽ More Graph distillation (GD) is an effective approach to extract useful information from large-scale network structures. However, existing methods, which operate in Euclidean space to generate condensed graphs, struggle to capture the inherent tree-like geometry of real-world networks, resulting in distilled graphs with limited task-specific information for downstream tasks. Furthermore, these methods often fail to extract dynamic properties from graphs, which are crucial for understanding information flow and facilitating graph continual learning. This paper presents the Hyperbolic Graph Distillation with Random Walks Optimization (HyDRO), a novel graph distillation approach that leverages hyperbolic embeddings to capture complex geometric patterns and optimize the spectral gap in hyperbolic space. Experiments show that HyDRO demonstrates strong task generalization, consistently outperforming state-of-the-art methods in both node classification and link prediction tasks. HyDRO also effectively preserves graph random walk properties, producing condensed graphs that achieve enhanced performance in continual graph learning. Additionally, HyDRO achieves competitive results on mainstream graph distillation benchmarks, while maintaining a strong balance between privacy and utility, and exhibiting robust resistance to noises. △ Less

Submitted 26 January, 2025; originally announced January 2025.

Enhancing Supply Chain Visibility with Generative AI: An Exploratory Case Study on Relationship Prediction in Knowledge Graphs

Authors: Ge Zheng, Alexandra Brintrup

Abstract: A key stumbling block in effective supply chain risk management for companies and policymakers is a lack of visibility on interdependent supply network relationships. Relationship prediction, also called link prediction is an emergent area of supply chain surveillance research that aims to increase the visibility of supply chains using data-driven techniques. Existing methods have been successful… ▽ More A key stumbling block in effective supply chain risk management for companies and policymakers is a lack of visibility on interdependent supply network relationships. Relationship prediction, also called link prediction is an emergent area of supply chain surveillance research that aims to increase the visibility of supply chains using data-driven techniques. Existing methods have been successful for predicting relationships but struggle to extract the context in which these relationships are embedded - such as the products being supplied or locations they are supplied from. Lack of context prevents practitioners from distinguishing transactional relations from established supply chain relations, hindering accurate estimations of risk. In this work, we develop a new Generative Artificial Intelligence (Gen AI) enhanced machine learning framework that leverages pre-trained language models as embedding models combined with machine learning models to predict supply chain relationships within knowledge graphs. By integrating Generative AI techniques, our approach captures the nuanced semantic relationships between entities, thereby improving supply chain visibility and facilitating more precise risk management. Using data from a real case study, we show that GenAI-enhanced link prediction surpasses all benchmarks, and demonstrate how GenAI models can be explored and effectively used in supply chain risk management. △ Less

Submitted 4 December, 2024; originally announced December 2024.

Comments: 18 pages, 5 figures

Agentic LLMs in the Supply Chain: Towards Autonomous Multi-Agent Consensus-Seeking

Authors: Valeria Jannelli, Stefan Schoepf, Matthias Bickel, Torbjørn Netland, Alexandra Brintrup

Abstract: This paper explores how Large Language Models (LLMs) can automate consensus-seeking in supply chain management (SCM), where frequent decisions on problems such as inventory levels and delivery times require coordination among companies. Traditional SCM relies on human consensus in decision-making to avoid emergent problems like the bullwhip effect. Some routine consensus processes, especially thos… ▽ More This paper explores how Large Language Models (LLMs) can automate consensus-seeking in supply chain management (SCM), where frequent decisions on problems such as inventory levels and delivery times require coordination among companies. Traditional SCM relies on human consensus in decision-making to avoid emergent problems like the bullwhip effect. Some routine consensus processes, especially those that are time-intensive and costly, can be automated. Existing solutions for automated coordination have faced challenges due to high entry barriers locking out SMEs, limited capabilities, and limited adaptability in complex scenarios. However, recent advances in Generative AI, particularly LLMs, show promise in overcoming these barriers. LLMs, trained on vast datasets can negotiate, reason, and plan, facilitating near-human-level consensus at scale with minimal entry barriers. In this work, we identify key limitations in existing approaches and propose autonomous LLM agents to address these gaps. We introduce a series of novel, supply chain-specific consensus-seeking frameworks tailored for LLM agents and validate the effectiveness of our approach through a case study in inventory management. To accelerate progress within the SCM community, we open-source our code, providing a foundation for further advancements in LLM-powered autonomous supply chain solutions. △ Less

Submitted 15 November, 2024; originally announced November 2024.

ConDa: Fast Federated Unlearning with Contribution Dampening

Authors: Vikram S Chundawat, Pushkar Niroula, Prasanna Dhungana, Stefan Schoepf, Murari Mandal, Alexandra Brintrup

Abstract: Federated learning (FL) has enabled collaborative model training across decentralized data sources or clients. While adding new participants to a shared model does not pose great technical hurdles, the removal of a participant and their related information contained in the shared model remains a challenge. To address this problem, federated unlearning has emerged as a critical research direction,… ▽ More Federated learning (FL) has enabled collaborative model training across decentralized data sources or clients. While adding new participants to a shared model does not pose great technical hurdles, the removal of a participant and their related information contained in the shared model remains a challenge. To address this problem, federated unlearning has emerged as a critical research direction, seeking to remove information from globally trained models without harming the model performance on the remaining data. Most modern federated unlearning methods use costly approaches such as the use of remaining clients data to retrain the global model or methods that would require heavy computation on client or server side. We introduce Contribution Dampening (ConDa), a framework that performs efficient unlearning by tracking down the parameters which affect the global model for each client and performs synaptic dampening on the parameters of the global model that have privacy infringing contributions from the forgetting client. Our technique does not require clients data or any kind of retraining and it does not put any computational overhead on either the client or server side. We perform experiments on multiple datasets and demonstrate that ConDa is effective to forget a client's data. In experiments conducted on the MNIST, CIFAR10, and CIFAR100 datasets, ConDa proves to be the fastest federated unlearning method, outperforming the nearest state of the art approach by at least 100x. Our emphasis is on the non-IID Federated Learning setting, which presents the greatest challenge for unlearning. Additionally, we validate ConDa's robustness through backdoor and membership inference attacks. We envision this work as a crucial component for FL in adhering to legal and ethical requirements. △ Less

Submitted 5 October, 2024; originally announced October 2024.

Leveraging Unsupervised Learning for Cost-Effective Visual Anomaly Detection

Authors: Yunbo Long, Zhengyang Ling, Sam Brook, Duncan McFarlane, Alexandra Brintrup

Abstract: Traditional machine learning-based visual inspection systems require extensive data collection and repetitive model training to improve accuracy. These systems typically require expensive camera, computing equipment and significant machine learning expertise, which can substantially burden small and medium-sized enterprises. This study explores leveraging unsupervised learning methods with pre-tra… ▽ More Traditional machine learning-based visual inspection systems require extensive data collection and repetitive model training to improve accuracy. These systems typically require expensive camera, computing equipment and significant machine learning expertise, which can substantially burden small and medium-sized enterprises. This study explores leveraging unsupervised learning methods with pre-trained models and low-cost hardware to create a cost-effective visual anomaly detection system. The research aims to develop a low-cost visual anomaly detection solution that uses minimal data for model training while maintaining generalizability and scalability. The system utilises unsupervised learning models from Anomalib and is deployed on affordable Raspberry Pi hardware through openVINO. The results show that this cost-effective system can complete anomaly defection training and inference on a Raspberry Pi in just 90 seconds using only 10 normal product images, achieving an F1 macro score exceeding 0.95. While the system is slightly sensitive to environmental changes like lighting, product positioning, or background, it remains a swift and economical method for factory automation inspection for small and medium-sized manufacturers. The code is available at https://github.com/Yunbo-max/Cost-Effective-Visual-Anomaly-Detection-using-Unsupervised-Learning. △ Less

Submitted 17 May, 2026; v1 submitted 24 September, 2024; originally announced September 2024.

What if? Causal Machine Learning in Supply Chain Risk Management

Authors: Mateusz Wyrembek, George Baryannis, Alexandra Brintrup

Abstract: The penultimate goal for developing machine learning models in supply chain management is to make optimal interventions. However, most machine learning models identify correlations in data rather than inferring causation, making it difficult to systematically plan for better outcomes. In this article, we propose and evaluate the use of causal machine learning for developing supply chain risk inter… ▽ More The penultimate goal for developing machine learning models in supply chain management is to make optimal interventions. However, most machine learning models identify correlations in data rather than inferring causation, making it difficult to systematically plan for better outcomes. In this article, we propose and evaluate the use of causal machine learning for developing supply chain risk intervention models, and demonstrate its use with a case study in supply chain risk management in the maritime engineering sector. Our findings highlight that causal machine learning enhances decision-making processes by identifying changes that can be achieved under different supply chain interventions, allowing "what-if" scenario planning. We therefore propose different machine learning developmental pathways for for predicting risk, and planning for interventions to minimise risk and outline key steps for supply chain researchers to explore causal machine learning. △ Less

Submitted 24 August, 2024; originally announced August 2024.

Enhancing Supply Chain Visibility with Knowledge Graphs and Large Language Models

Authors: Sara AlMahri, Liming Xu, Alexandra Brintrup

Abstract: In today's globalized economy, comprehensive supply chain visibility is crucial for effective risk management. Achieving visibility remains a significant challenge due to limited information sharing among supply chain partners. This paper presents a novel framework leveraging Knowledge Graphs (KGs) and Large Language Models (LLMs) to enhance supply chain visibility without relying on direct stakeh… ▽ More In today's globalized economy, comprehensive supply chain visibility is crucial for effective risk management. Achieving visibility remains a significant challenge due to limited information sharing among supply chain partners. This paper presents a novel framework leveraging Knowledge Graphs (KGs) and Large Language Models (LLMs) to enhance supply chain visibility without relying on direct stakeholder information sharing. Our zero-shot, LLM-driven approach automates the extraction of supply chain information from diverse public sources and constructs KGs to capture complex interdependencies between supply chain entities. We employ zero-shot prompting for Named Entity Recognition (NER) and Relation Extraction (RE) tasks, eliminating the need for extensive domain-specific training. We validate the framework with a case study on electric vehicle supply chains, focusing on tracking critical minerals for battery manufacturing. Results show significant improvements in supply chain mapping, extending visibility beyond tier-2 suppliers. The framework reveals critical dependencies and alternative sourcing options, enhancing risk management and strategic planning. With high accuracy in NER and RE tasks, it provides an effective tool for understanding complex, multi-tiered supply networks. This research offers a scalable, flexible method for constructing domain-specific supply chain KGs, addressing longstanding challenges in visibility and paving the way for advancements in digital supply chain surveillance. △ Less

Submitted 5 August, 2024; originally announced August 2024.

Potion: Towards Poison Unlearning

Authors: Stefan Schoepf, Jack Foster, Alexandra Brintrup

Abstract: Adversarial attacks by malicious actors on machine learning systems, such as introducing poison triggers into training datasets, pose significant risks. The challenge in resolving such an attack arises in practice when only a subset of the poisoned data can be identified. This necessitates the development of methods to remove, i.e. unlearn, poison triggers from already trained models with only a s… ▽ More Adversarial attacks by malicious actors on machine learning systems, such as introducing poison triggers into training datasets, pose significant risks. The challenge in resolving such an attack arises in practice when only a subset of the poisoned data can be identified. This necessitates the development of methods to remove, i.e. unlearn, poison triggers from already trained models with only a subset of the poison data available. The requirements for this task significantly deviate from privacy-focused unlearning where all of the data to be forgotten by the model is known. Previous work has shown that the undiscovered poisoned samples lead to a failure of established unlearning methods, with only one method, Selective Synaptic Dampening (SSD), showing limited success. Even full retraining, after the removal of the identified poison, cannot address this challenge as the undiscovered poison samples lead to a reintroduction of the poison trigger in the model. Our work addresses two key challenges to advance the state of the art in poison unlearning. First, we introduce a novel outlier-resistant method, based on SSD, that significantly improves model protection and unlearning performance. Second, we introduce Poison Trigger Neutralisation (PTN) search, a fast, parallelisable, hyperparameter search that utilises the characteristic "unlearning versus model protection" trade-off to find suitable hyperparameters in settings where the forget set size is unknown and the retain set is contaminated. We benchmark our contributions using ResNet-9 on CIFAR10 and WideResNet-28x10 on CIFAR100. Experimental results show that our method heals 93.72% of poison compared to SSD with 83.41% and full retraining with 40.68%. We achieve this while also lowering the average model accuracy drop caused by unlearning from 5.68% (SSD) to 1.41% (ours). △ Less

Submitted 11 September, 2024; v1 submitted 13 June, 2024; originally announced June 2024.

Comments: Accepted for publication in the Journal of Data-centric Machine Learning Research (DMLR) https://openreview.net/forum?id=4eSiRnWWaF

Loss-Free Machine Unlearning

Authors: Jack Foster, Stefan Schoepf, Alexandra Brintrup

Abstract: We present a machine unlearning approach that is both retraining- and label-free. Most existing machine unlearning approaches require a model to be fine-tuned to remove information while preserving performance. This is computationally expensive and necessitates the storage of the whole dataset for the lifetime of the model. Retraining-free approaches often utilise Fisher information, which is deri… ▽ More We present a machine unlearning approach that is both retraining- and label-free. Most existing machine unlearning approaches require a model to be fine-tuned to remove information while preserving performance. This is computationally expensive and necessitates the storage of the whole dataset for the lifetime of the model. Retraining-free approaches often utilise Fisher information, which is derived from the loss and requires labelled data which may not be available. Thus, we present an extension to the Selective Synaptic Dampening algorithm, substituting the diagonal of the Fisher information matrix for the gradient of the l2 norm of the model output to approximate sensitivity. We evaluate our method in a range of experiments using ResNet18 and Vision Transformer. Results show our label-free method is competitive with existing state-of-the-art approaches. △ Less

Submitted 29 February, 2024; originally announced February 2024.

Comments: Accepted as a Tiny Paper at ICLR 2024

Parameter-tuning-free data entry error unlearning with adaptive selective synaptic dampening

Authors: Stefan Schoepf, Jack Foster, Alexandra Brintrup

Abstract: Data entry constitutes a fundamental component of the machine learning pipeline, yet it frequently results in the introduction of labelling errors. When a model has been trained on a dataset containing such errors its performance is reduced. This leads to the challenge of efficiently unlearning the influence of the erroneous data to improve the model performance without needing to completely retra… ▽ More Data entry constitutes a fundamental component of the machine learning pipeline, yet it frequently results in the introduction of labelling errors. When a model has been trained on a dataset containing such errors its performance is reduced. This leads to the challenge of efficiently unlearning the influence of the erroneous data to improve the model performance without needing to completely retrain the model. While model editing methods exist for cases in which the correct label for a wrong entry is known, we focus on the case of data entry errors where we do not know the correct labels for the erroneous data. Our contribution is twofold. First, we introduce an extension to the selective synaptic dampening unlearning method that removes the need for parameter tuning, making unlearning accessible to practitioners. We demonstrate the performance of this extension, adaptive selective synaptic dampening (ASSD), on various ResNet18 and Vision Transformer unlearning tasks. Second, we demonstrate the performance of ASSD in a supply chain delay prediction problem with labelling errors using real-world data where we randomly introduce various levels of labelling errors. The application of this approach is particularly compelling in industrial settings, such as supply chain management, where a significant portion of data entry occurs manually through Excel sheets, rendering it error-prone. ASSD shows strong performance on general unlearning benchmarks and on the error correction problem where it outperforms fine-tuning for error correction. △ Less

Submitted 6 February, 2024; originally announced February 2024.

An Information Theoretic Approach to Machine Unlearning

Authors: Jack Foster, Kyle Fogarty, Stefan Schoepf, Zack Dugue, Cengiz Öztireli, Alexandra Brintrup

Abstract: To comply with AI and data regulations, the need to forget private or copyrighted information from trained machine learning models is increasingly important. The key challenge in unlearning is forgetting the necessary data in a timely manner, while preserving model performance. In this work, we address the zero-shot unlearning scenario, whereby an unlearning algorithm must be able to remove data g… ▽ More To comply with AI and data regulations, the need to forget private or copyrighted information from trained machine learning models is increasingly important. The key challenge in unlearning is forgetting the necessary data in a timely manner, while preserving model performance. In this work, we address the zero-shot unlearning scenario, whereby an unlearning algorithm must be able to remove data given only a trained model and the data to be forgotten. We explore unlearning from an information theoretic perspective, connecting the influence of a sample to the information gain a model receives by observing it. From this, we derive a simple but principled zero-shot unlearning method based on the geometry of the model. Our approach takes the form of minimising the gradient of a learned function with respect to a small neighbourhood around a target forget point. This induces a smoothing effect, causing forgetting by moving the boundary of the classifier. We explore the intuition behind why this approach can jointly unlearn forget samples while preserving general model performance through a series of low-dimensional experiments. We perform extensive empirical evaluation of our method over a range of contemporary benchmarks, verifying that our method is competitive with state-of-the-art performance under the strict constraints of zero-shot unlearning. Code for the project can be found at https://github.com/jwf40/Information-Theoretic-Unlearning △ Less

Submitted 1 December, 2024; v1 submitted 2 February, 2024; originally announced February 2024.

Comments: Updated, new low-dimensional experiments and updated perspective on unlearning from an information theoretic view

Towards Autonomous Supply Chains: Definition, Characteristics, Conceptual Framework, and Autonomy Levels

Authors: Liming Xu, Stephen Mak, Yaniv Proselkov, Alexandra Brintrup

Abstract: Recent global disruptions, such as the pandemic and geopolitical conflicts, have profoundly exposed vulnerabilities in traditional supply chains, requiring exploration of more resilient alternatives. Autonomous supply chains (ASCs) have emerged as a potential solution, offering increased visibility, flexibility, and resilience in turbulent trade environments. Despite discussions in industry and ac… ▽ More Recent global disruptions, such as the pandemic and geopolitical conflicts, have profoundly exposed vulnerabilities in traditional supply chains, requiring exploration of more resilient alternatives. Autonomous supply chains (ASCs) have emerged as a potential solution, offering increased visibility, flexibility, and resilience in turbulent trade environments. Despite discussions in industry and academia over several years, ASCs lack well-established theoretical foundations. This paper addresses this research gap by presenting a formal definition of ASC along with its defining characteristics and auxiliary concepts. We propose a layered conceptual framework called the MIISI model. An illustrative case study focusing on the meat supply chain demonstrates an initial ASC implementation based on this conceptual model. Additionally, we introduce a seven-level supply chain autonomy reference model, delineating a trajectory towards achieving a full supply chain autonomy. Recognising that this work represents an initial endeavour, we emphasise the need for continued exploration in this emerging domain. We anticipate that this work will stimulate further research, both theoretical and technical, and contribute to the continual evolution of ASCs. △ Less

Submitted 25 September, 2024; v1 submitted 13 October, 2023; originally announced January 2024.

Comments: This paper includes 19 pages and 8 figures and has been accepted for publication in the Journal of Industrial Information Integration

Fair collaborative vehicle routing: A deep multi-agent reinforcement learning approach

Authors: Stephen Mak, Liming Xu, Tim Pearce, Michael Ostroumov, Alexandra Brintrup

Abstract: Collaborative vehicle routing occurs when carriers collaborate through sharing their transportation requests and performing transportation requests on behalf of each other. This achieves economies of scale, thus reducing cost, greenhouse gas emissions and road congestion. But which carrier should partner with whom, and how much should each carrier be compensated? Traditional game theoretic solutio… ▽ More Collaborative vehicle routing occurs when carriers collaborate through sharing their transportation requests and performing transportation requests on behalf of each other. This achieves economies of scale, thus reducing cost, greenhouse gas emissions and road congestion. But which carrier should partner with whom, and how much should each carrier be compensated? Traditional game theoretic solution concepts are expensive to calculate as the characteristic function scales exponentially with the number of agents. This would require solving the vehicle routing problem (NP-hard) an exponential number of times. We therefore propose to model this problem as a coalitional bargaining game solved using deep multi-agent reinforcement learning, where - crucially - agents are not given access to the characteristic function. Instead, we implicitly reason about the characteristic function; thus, when deployed in production, we only need to evaluate the expensive post-collaboration vehicle routing problem once. Our contribution is that we are the first to consider both the route allocation problem and gain sharing problem simultaneously - without access to the expensive characteristic function. Through decentralised machine learning, our agents bargain with each other and agree to outcomes that correlate well with the Shapley value - a fair profit allocation mechanism. Importantly, we are able to achieve a reduction in run-time of 88%. △ Less

Submitted 26 October, 2023; originally announced October 2023.

Comments: Final, published version can be found here: https://www.sciencedirect.com/science/article/pii/S0968090X23003662

Journal ref: Volume 157, December 2023, 104376

Coalitional Bargaining via Reinforcement Learning: An Application to Collaborative Vehicle Routing

Authors: Stephen Mak, Liming Xu, Tim Pearce, Michael Ostroumov, Alexandra Brintrup

Abstract: Collaborative Vehicle Routing is where delivery companies cooperate by sharing their delivery information and performing delivery requests on behalf of each other. This achieves economies of scale and thus reduces cost, greenhouse gas emissions, and road congestion. But which company should partner with whom, and how much should each company be compensated? Traditional game theoretic solution conc… ▽ More Collaborative Vehicle Routing is where delivery companies cooperate by sharing their delivery information and performing delivery requests on behalf of each other. This achieves economies of scale and thus reduces cost, greenhouse gas emissions, and road congestion. But which company should partner with whom, and how much should each company be compensated? Traditional game theoretic solution concepts, such as the Shapley value or nucleolus, are difficult to calculate for the real-world problem of Collaborative Vehicle Routing due to the characteristic function scaling exponentially with the number of agents. This would require solving the Vehicle Routing Problem (an NP-Hard problem) an exponential number of times. We therefore propose to model this problem as a coalitional bargaining game where - crucially - agents are not given access to the characteristic function. Instead, we implicitly reason about the characteristic function, and thus eliminate the need to evaluate the VRP an exponential number of times - we only need to evaluate it once. Our contribution is that our decentralised approach is both scalable and considers the self-interested nature of companies. The agents learn using a modified Independent Proximal Policy Optimisation. Our RL agents outperform a strong heuristic bot. The agents correctly identify the optimal coalitions 79% of the time with an average optimality gap of 4.2% and reduction in run-time of 62%. △ Less

Submitted 26 October, 2023; originally announced October 2023.

Comments: Accepted to NeurIPS 2021 Workshop on Cooperative AI

On Implementing Autonomous Supply Chains: a Multi-Agent System Approach

Authors: Liming Xu, Stephen Mak, Maria Minaricova, Alexandra Brintrup

Abstract: Trade restrictions, the COVID-19 pandemic, and geopolitical conflicts have significantly exposed vulnerabilities within traditional global supply chains. These events underscore the need for organisations to establish more resilient and flexible supply chains. To address these challenges, the concept of the autonomous supply chain (ASC), characterised by predictive and self-decision-making capabil… ▽ More Trade restrictions, the COVID-19 pandemic, and geopolitical conflicts have significantly exposed vulnerabilities within traditional global supply chains. These events underscore the need for organisations to establish more resilient and flexible supply chains. To address these challenges, the concept of the autonomous supply chain (ASC), characterised by predictive and self-decision-making capabilities, has recently emerged as a promising solution. However, research on ASCs is relatively limited, with no existing studies specifically focusing on their implementations. This paper aims to address this gap by presenting an implementation of ASC using a multi-agent approach. It presents a methodology for the analysis and design of such an agent-based ASC system (A2SC). This paper provides a concrete case study, the autonomous meat supply chain, which showcases the practical implementation of the A2SC system using the proposed methodology. Additionally, a system architecture and a toolkit for developing such A2SC systems are presented. Despite limitations, this work demonstrates a promising approach for implementing an effective ASC system. △ Less

Submitted 14 June, 2024; v1 submitted 13 October, 2023; originally announced October 2023.

Comments: This paper includes 32 pages and 14 figures and has been accepted to Computer in Industry for publication (in process)

Multi-Agent Digital Twinning for Collaborative Logistics: Framework and Implementation

Authors: Liming Xu, Stephen Mak, Stefan Schoepf, Michael Ostroumov, Alexandra Brintrup

Abstract: Collaborative logistics has been widely recognised as an effective avenue to reduce carbon emissions by enhanced truck utilisation and reduced travel distance. However, stakeholders' participation in collaborations is hindered by information-sharing barriers and the absence of integrated systems. We, thus, in this paper addresses these barriers by investigating an integrated platform that foster c… ▽ More Collaborative logistics has been widely recognised as an effective avenue to reduce carbon emissions by enhanced truck utilisation and reduced travel distance. However, stakeholders' participation in collaborations is hindered by information-sharing barriers and the absence of integrated systems. We, thus, in this paper addresses these barriers by investigating an integrated platform that foster collaboration through the integration of agents with digital twins. Specifically, we employ a multi-agent system approach to integrate stakeholders and physical mobile assets in collaborative logistics, representing them as agents. We introduce a loosely-coupled system architecture that facilitates the connection between physical and digital systems, enabling the integration of agents with digital twins. Using this architecture, we implement the platform (or testbed). The resulting testbed, comprising a physical environment and a digital replica, is a digital twin that integrates distributed entities involved in collaborative logistics. The effectiveness of the testbed is demonstrated through a carrier collaboration scenario. This paper is among the earliest few efforts to investigate the integration of agents and digital twin concepts and goes beyond the conceptual discussion of existing studies to the technical implementation of such integration. △ Less

Submitted 12 February, 2025; v1 submitted 22 September, 2023; originally announced September 2023.

Comments: This paper includes 23 pages, 14 figures, and has been accepted to the Journal of Industrial Information Integration for publication

Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization

Authors: Jack Foster, Alexandra Brintrup

Abstract: The pursuit of long-term autonomy mandates that machine learning models must continuously adapt to their changing environments and learn to solve new tasks. Continual learning seeks to overcome the challenge of catastrophic forgetting, where learning to solve new tasks causes a model to forget previously learnt information. Prior-based continual learning methods are appealing as they are computati… ▽ More The pursuit of long-term autonomy mandates that machine learning models must continuously adapt to their changing environments and learn to solve new tasks. Continual learning seeks to overcome the challenge of catastrophic forgetting, where learning to solve new tasks causes a model to forget previously learnt information. Prior-based continual learning methods are appealing as they are computationally efficient and do not require auxiliary models or data storage. However, prior-based approaches typically fail on important benchmarks and are thus limited in their potential applications compared to their memory-based counterparts. We introduce Bayesian adaptive moment regularization (BAdam), a novel prior-based method that better constrains parameter growth, reducing catastrophic forgetting. Our method boasts a range of desirable properties such as being lightweight and task label-free, converging quickly, and offering calibrated uncertainty that is important for safe real-world deployment. Results show that BAdam achieves state-of-the-art performance for prior-based methods on challenging single-headed class-incremental experiments such as Split MNIST and Split FashionMNIST, and does so without relying on task labels or discrete task boundaries. △ Less

Submitted 24 July, 2024; v1 submitted 15 September, 2023; originally announced September 2023.

Implementation of Autonomous Supply Chains for Digital Twinning: a Multi-Agent Approach

Authors: Liming Xu, Yaniv Proselkov, Stefan Schoepf, David Minarsch, Maria Minaricova, Alexandra Brintrup

Abstract: Trade disruptions, the pandemic, and the Ukraine war over the past years have adversely affected global supply chains, revealing their vulnerability. Autonomous supply chains are an emerging topic that has gained attention in industry and academia as a means of increasing their monitoring and robustness. While many theoretical frameworks exist, there is only sparse work to facilitate generalisable… ▽ More Trade disruptions, the pandemic, and the Ukraine war over the past years have adversely affected global supply chains, revealing their vulnerability. Autonomous supply chains are an emerging topic that has gained attention in industry and academia as a means of increasing their monitoring and robustness. While many theoretical frameworks exist, there is only sparse work to facilitate generalisable technical implementation. We address this gap by investigating multi-agent system approaches for implementing autonomous supply chains, presenting an autonomous economic agent-based technical framework. We illustrate this framework with a prototype, studied in a perishable food supply chain scenario, and discuss possible extensions. △ Less

Submitted 9 September, 2023; originally announced September 2023.

Comments: This paper includes 7 Pages, 4 Figures, and has been accepted by the IFAC World Congress 2023, 9 July - 14 July, 2023, Yokohama, Japan and will be published in IFAC-PapersOnLine

Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening

Authors: Jack Foster, Stefan Schoepf, Alexandra Brintrup

Abstract: Machine unlearning, the ability for a machine learning model to forget, is becoming increasingly important to comply with data privacy regulations, as well as to remove harmful, manipulated, or outdated information. The key challenge lies in forgetting specific information while protecting model performance on the remaining data. While current state-of-the-art methods perform well, they typically… ▽ More Machine unlearning, the ability for a machine learning model to forget, is becoming increasingly important to comply with data privacy regulations, as well as to remove harmful, manipulated, or outdated information. The key challenge lies in forgetting specific information while protecting model performance on the remaining data. While current state-of-the-art methods perform well, they typically require some level of retraining over the retained data, in order to protect or restore model performance. This adds computational overhead and mandates that the training data remain available and accessible, which may not be feasible. In contrast, other methods employ a retrain-free paradigm, however, these approaches are prohibitively computationally expensive and do not perform on par with their retrain-based counterparts. We present Selective Synaptic Dampening (SSD), a novel two-step, post hoc, retrain-free approach to machine unlearning which is fast, performant, and does not require long-term storage of the training data. First, SSD uses the Fisher information matrix of the training and forgetting data to select parameters that are disproportionately important to the forget set. Second, SSD induces forgetting by dampening these parameters proportional to their relative importance to the forget set with respect to the wider training data. We evaluate our method against several existing unlearning methods in a range of experiments using ResNet18 and Vision Transformer. Results show that the performance of SSD is competitive with retrain-based post hoc methods, demonstrating the viability of retrain-free post hoc unlearning approaches. △ Less

Submitted 13 December, 2023; v1 submitted 15 August, 2023; originally announced August 2023.

Comments: Accepted as a main track paper at AAAI 2024

Identifying contributors to supply chain outcomes in a multi-echelon setting: a decentralised approach

Authors: Stefan Schoepf, Jack Foster, Alexandra Brintrup

Abstract: Organisations often struggle to identify the causes of change in metrics such as product quality and delivery duration. This task becomes increasingly challenging when the cause lies outside of company borders in multi-echelon supply chains that are only partially observable. Although traditional supply chain management has advocated for data sharing to gain better insights, this does not take pla… ▽ More Organisations often struggle to identify the causes of change in metrics such as product quality and delivery duration. This task becomes increasingly challenging when the cause lies outside of company borders in multi-echelon supply chains that are only partially observable. Although traditional supply chain management has advocated for data sharing to gain better insights, this does not take place in practice due to data privacy concerns. We propose the use of explainable artificial intelligence for decentralised computing of estimated contributions to a metric of interest in a multi-stage production process. This approach mitigates the need to convince supply chain actors to share data, as all computations occur in a decentralised manner. Our method is empirically validated using data collected from a real multi-stage manufacturing process. The results demonstrate the effectiveness of our approach in detecting the source of quality variations compared to a centralised approach using Shapley additive explanations. △ Less

Submitted 15 August, 2024; v1 submitted 22 July, 2023; originally announced July 2023.

Comments: Accepted to appear in IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (Manuscript Version according to the UKRI IEEE Green Open Access Policy)

Using Reinforcement Learning for the Three-Dimensional Loading Capacitated Vehicle Routing Problem

Authors: Stefan Schoepf, Stephen Mak, Julian Senoner, Liming Xu, Netland Torbjörn, Alexandra Brintrup

Abstract: Heavy goods vehicles are vital backbones of the supply chain delivery system but also contribute significantly to carbon emissions with only 60% loading efficiency in the United Kingdom. Collaborative vehicle routing has been proposed as a solution to increase efficiency, but challenges remain to make this a possibility. One key challenge is the efficient computation of viable solutions for co-loa… ▽ More Heavy goods vehicles are vital backbones of the supply chain delivery system but also contribute significantly to carbon emissions with only 60% loading efficiency in the United Kingdom. Collaborative vehicle routing has been proposed as a solution to increase efficiency, but challenges remain to make this a possibility. One key challenge is the efficient computation of viable solutions for co-loading and routing. Current operations research methods suffer from non-linear scaling with increasing problem size and are therefore bound to limited geographic areas to compute results in time for day-to-day operations. This only allows for local optima in routing and leaves global optimisation potential untouched. We develop a reinforcement learning model to solve the three-dimensional loading capacitated vehicle routing problem in approximately linear time. While this problem has been studied extensively in operations research, no publications on solving it with reinforcement learning exist. We demonstrate the favourable scaling of our reinforcement learning model and benchmark our routing performance against state-of-the-art methods. The model performs within an average gap of 3.83% to 8.10% compared to established methods. Our model not only represents a promising first step towards large-scale logistics optimisation with reinforcement learning but also lays the foundation for this research stream. GitHub: https://github.com/if-loops/3L-CVRP △ Less

Submitted 11 June, 2024; v1 submitted 22 July, 2023; originally announced July 2023.

Comments: Presented at the IJCAI 2023 Workshop on Search and Planning with Complex Objectives (WoSePCO)

Trustworthy, responsible, ethical AI in manufacturing and supply chains: synthesis and emerging research questions

Authors: Alexandra Brintrup, George Baryannis, Ashutosh Tiwari, Svetan Ratchev, Giovanna Martinez-Arellano, Jatinder Singh

Abstract: While the increased use of AI in the manufacturing sector has been widely noted, there is little understanding on the risks that it may raise in a manufacturing organisation. Although various high level frameworks and definitions have been proposed to consolidate potential risks, practitioners struggle with understanding and implementing them. This lack of understanding exposes manufacturing to… ▽ More While the increased use of AI in the manufacturing sector has been widely noted, there is little understanding on the risks that it may raise in a manufacturing organisation. Although various high level frameworks and definitions have been proposed to consolidate potential risks, practitioners struggle with understanding and implementing them. This lack of understanding exposes manufacturing to a multitude of risks, including the organisation, its workers, as well as suppliers and clients. In this paper, we explore and interpret the applicability of responsible, ethical, and trustworthy AI within the context of manufacturing. We then use a broadened adaptation of a machine learning lifecycle to discuss, through the use of illustrative examples, how each step may result in a given AI trustworthiness concern. We additionally propose a number of research questions to the manufacturing research community, in order to help guide future research so that the economic and societal benefits envisaged by AI in manufacturing are delivered safely and responsibly. △ Less

Submitted 19 May, 2023; originally announced May 2023.

Comments: Pre-print under peer-review

Journal ref: Data-Centric Engineering 6 (2025) e53

Network science approach for identifying disruptive elements of an airline

Authors: Vinod Kumar Chauhan, Anna Ledwoch, Alexandra Brintrup, Manuel Herrera, Vaggelis Giannikas, Goran Stojkovic, Duncan Mcfarlane

Abstract: Currently, flight delays are common and they propagate from an originating flight to connecting flights, leading to large disruptions in the overall schedule. These disruptions cause massive economic losses, affect airlines' reputations, waste passengers' time and money, and directly impact the environment. This study adopts a network science approach for solving the delay propagation problem by m… ▽ More Currently, flight delays are common and they propagate from an originating flight to connecting flights, leading to large disruptions in the overall schedule. These disruptions cause massive economic losses, affect airlines' reputations, waste passengers' time and money, and directly impact the environment. This study adopts a network science approach for solving the delay propagation problem by modeling and analyzing the flight schedules and historical operational data of an airline. We aim to determine the most disruptive airports, flights, flight-connections, and connection types in an airline network. Disruptive elements are influential or critical entities in an airline network. They are the elements that can either cause (airline schedules) or have caused (historical data) the largest disturbances in the network. An airline can improve its operations by avoiding delays caused by the most disruptive elements. The proposed network science approach for disruptive element analysis was validated using a case study of an operating airline. The analysis indicates that potential disruptive elements in a schedule of an airline are also actual disruptive elements in the historical data and they should be considered to improve operations. The airline network exhibits small-world effects and delays can propagate to any part of the network with a minimum of four delayed flights. Finally, we observed that passenger connections between flights are the most disruptive connection type. Therefore, the proposed methodology provides a tool for airlines to build robust flight schedules that reduce delays and propagation. △ Less

Submitted 14 April, 2023; v1 submitted 19 October, 2022; originally announced November 2022.

Comments: accepted to Data Science and Management

Real-time large-scale supplier order assignments across two-tiers of a supply chain with penalty and dual-sourcing

Authors: Vinod Kumar Chauhan, Stephen Mak, Ajith Kumar Parlikad, Muhannad Alomari, Linus Casassa, Alexandra Brintrup

Abstract: Supplier selection and order allocation (SSOA) are key strategic decisions in supply chain management which greatly impact the performance of the supply chain. Although, the SSOA problem has been studied extensively but less attention paid to scalability presents a significant gap preventing adoption of SSOA algorithms by industrial practitioners. This paper presents a novel multi-item, multi-supp… ▽ More Supplier selection and order allocation (SSOA) are key strategic decisions in supply chain management which greatly impact the performance of the supply chain. Although, the SSOA problem has been studied extensively but less attention paid to scalability presents a significant gap preventing adoption of SSOA algorithms by industrial practitioners. This paper presents a novel multi-item, multi-supplier double order allocations with dual-sourcing and penalty constraints across two-tiers of a supply chain, resulting in cooperation and in facilitating supplier preferences to work with other suppliers through bidding. We propose Mixed-Integer Programming models for allocations at individual-tiers as well as an integrated allocations. An application to a real-time large-scale case study of a manufacturing company is presented, which is the largest scale studied in terms of supply chain size and number of variables so far in literature. The use case allows us to highlight how problem formulation and implementation can help reduce computational complexity using Mathematical Programming (MP) and Genetic Algorithm (GA) approaches. The results show an interesting observation that MP outperforms GA to solve SSOA. Sensitivity analysis is presented for sourcing strategy, penalty threshold and penalty factor. The developed model was successfully deployed in a large international sourcing conference with multiple bidding rounds, which helped in more than 10% procurement cost reductions to the manufacturing company. △ Less

Submitted 30 December, 2022; v1 submitted 21 October, 2022; originally announced October 2022.

Comments: accepted at Computers & Industrial Engineering (2022)

Exploitation of material consolidation trade-offs in multi-tier complex supply networks

Authors: Vinod Kumar Chauhan, Muhannad Alomari, James Arney, Ajith Kumar Parlikad, Alexandra Brintrup

Abstract: While consolidation strategies form the backbone of many supply chain optimisation problems, exploitation of multi-tier material relationships through consolidation remains an understudied area, despite being a prominent feature of industries that produce complex made-to-order products. In this paper, we propose an optimisation framework for exploiting multi-to-multi relationship between tiers of… ▽ More While consolidation strategies form the backbone of many supply chain optimisation problems, exploitation of multi-tier material relationships through consolidation remains an understudied area, despite being a prominent feature of industries that produce complex made-to-order products. In this paper, we propose an optimisation framework for exploiting multi-to-multi relationship between tiers of a supply chain. The resulting formulation is flexible such that quantity discounts, inventory holding, and transport costs can be included. The framework introduces a new trade-off between tiers, leading to cost reductions in one tier but increased costs in the other, which helps to reduce the overall procurement cost in the supply chain. A mixed integer linear programming model is developed and tested with a range of small to large-scale test problems from aerospace manufacturing. Our comparison to benchmark results shows that there is indeed a cost trade-off between two tiers, and that its reduction can be achieved using a holistic approach to reconfiguration. Costs are decreased when second tier fixed ordering costs and the number of machining options increase. Consolidation results in reduced inventory holding costs in all scenarios. Several secondary effects such as simplified supplier selection may also be observed. △ Less

Submitted 19 November, 2023; v1 submitted 19 October, 2022; originally announced October 2022.

Comments: accepted to Supply Chain Analytics

Journal ref: Supply Chain Analytics, Volume 4, December 2023, 100050

Trolley Optimisation for Loading Printed Circuit Board Components

Authors: Vinod Kumar Chauhan, Mark Bass, Ajith Kumar Parlikad, Alexandra Brintrup

Abstract: A trolley is a container for loading printed circuit board (PCB) components, and a trolley optimisation problem (TOP) is an assignment of PCB components to trolleys for use in the production of a set of PCBs in an assembly line. In this paper, we introduce the TOP, a novel operation research application. To formulate the TOP, we derive a novel extension of the bin packing problem. We exploit the p… ▽ More A trolley is a container for loading printed circuit board (PCB) components, and a trolley optimisation problem (TOP) is an assignment of PCB components to trolleys for use in the production of a set of PCBs in an assembly line. In this paper, we introduce the TOP, a novel operation research application. To formulate the TOP, we derive a novel extension of the bin packing problem. We exploit the problem structure to decompose the TOP into two smaller, identical, and independent problems. Further, we develop a mixed integer linear programming model to solve the TOP and prove that the TOP is an NP-complete problem. A case study of an aerospace manufacturing company is used to illustrate the TOP which successfully automated the manual process in the company and resulted in significant cost reductions and flexibility in the building process. △ Less

Submitted 13 August, 2024; v1 submitted 19 September, 2022; originally announced September 2022.

Comments: Accepted to Operations Research Forum (Springer Nature)

Journal ref: Operations Research Forum, Volume 5 (72), 2024

Bayesian autoencoders with uncertainty quantification: Towards trustworthy anomaly detection

Authors: Bang Xiang Yong, Alexandra Brintrup

Abstract: Despite numerous studies of deep autoencoders (AEs) for unsupervised anomaly detection, AEs still lack a way to express uncertainty in their predictions, crucial for ensuring safe and trustworthy machine learning systems in high-stake applications. Therefore, in this work, the formulation of Bayesian autoencoders (BAEs) is adopted to quantify the total anomaly uncertainty, comprising epistemic and… ▽ More Despite numerous studies of deep autoencoders (AEs) for unsupervised anomaly detection, AEs still lack a way to express uncertainty in their predictions, crucial for ensuring safe and trustworthy machine learning systems in high-stake applications. Therefore, in this work, the formulation of Bayesian autoencoders (BAEs) is adopted to quantify the total anomaly uncertainty, comprising epistemic and aleatoric uncertainties. To evaluate the quality of uncertainty, we consider the task of classifying anomalies with the additional option of rejecting predictions of high uncertainty. In addition, we use the accuracy-rejection curve and propose the weighted average accuracy as a performance metric. Our experiments demonstrate the effectiveness of the BAE and total anomaly uncertainty on a set of benchmark datasets and two real datasets for manufacturing: one for condition monitoring, the other for quality inspection. △ Less

Submitted 25 February, 2022; originally announced February 2022.

Do autoencoders need a bottleneck for anomaly detection?

Authors: Bang Xiang Yong, Alexandra Brintrup

Abstract: A common belief in designing deep autoencoders (AEs), a type of unsupervised neural network, is that a bottleneck is required to prevent learning the identity function. Learning the identity function renders the AEs useless for anomaly detection. In this work, we challenge this limiting belief and investigate the value of non-bottlenecked AEs. The bottleneck can be removed in two ways: (1) overp… ▽ More A common belief in designing deep autoencoders (AEs), a type of unsupervised neural network, is that a bottleneck is required to prevent learning the identity function. Learning the identity function renders the AEs useless for anomaly detection. In this work, we challenge this limiting belief and investigate the value of non-bottlenecked AEs. The bottleneck can be removed in two ways: (1) overparameterising the latent layer, and (2) introducing skip connections. However, limited works have reported on the use of one of the ways. For the first time, we carry out extensive experiments covering various combinations of bottleneck removal schemes, types of AEs and datasets. In addition, we propose the infinitely-wide AEs as an extreme example of non-bottlenecked AEs. Their improvement over the baseline implies learning the identity function is not trivial as previously assumed. Moreover, we find that non-bottlenecked architectures (highest AUROC=0.857) can outperform their bottlenecked counterparts (highest AUROC=0.696) on the popular task of CIFAR (inliers) vs SVHN (anomalies), among other tasks, shedding light on the potential of developing non-bottlenecked AEs for improving anomaly detection. △ Less

Submitted 25 February, 2022; originally announced February 2022.

Coalitional Bayesian Autoencoders -- Towards explainable unsupervised deep learning

Authors: Bang Xiang Yong, Alexandra Brintrup

Abstract: This paper aims to improve the explainability of Autoencoder's (AE) predictions by proposing two explanation methods based on the mean and epistemic uncertainty of log-likelihood estimate, which naturally arise from the probabilistic formulation of the AE called Bayesian Autoencoders (BAE). To quantitatively evaluate the performance of explanation methods, we test them in sensor network applicatio… ▽ More This paper aims to improve the explainability of Autoencoder's (AE) predictions by proposing two explanation methods based on the mean and epistemic uncertainty of log-likelihood estimate, which naturally arise from the probabilistic formulation of the AE called Bayesian Autoencoders (BAE). To quantitatively evaluate the performance of explanation methods, we test them in sensor network applications, and propose three metrics based on covariate shift of sensors : (1) G-mean of Spearman drift coefficients, (2) G-mean of sensitivity-specificity of explanation ranking and (3) sensor explanation quality index (SEQI) which combines the two aforementioned metrics. Surprisingly, we find that explanations of BAE's predictions suffer from high correlation resulting in misleading explanations. To alleviate this, a "Coalitional BAE" is proposed, which is inspired by agent-based system theory. Our comprehensive experiments on publicly available condition monitoring datasets demonstrate the improved quality of explanations using the Coalitional BAE. △ Less

Submitted 19 October, 2021; originally announced October 2021.

Comments: Preprint submitted to Journal of Applied Soft Computing