Showing 1–50 of 50 results for author: Agrawal, N

Benchmarking KV-Cache Optimizations across Task Quality and System Performance for Long-Context Serving

Authors: Nikita Agrawal, Ruben Mayer

Abstract: Large language model serving is increasingly limited by KV-cache growth under long-context workloads, yet existing KV-cache compression techniques are difficult to compare because they were evaluated on different models, tasks, budgets, and serving stacks. This paper presents a workload-aware benchmark of representative KV-cache optimization mechanisms spanning quantization, pruning, and merging,… ▽ More Large language model serving is increasingly limited by KV-cache growth under long-context workloads, yet existing KV-cache compression techniques are difficult to compare because they were evaluated on different models, tasks, budgets, and serving stacks. This paper presents a workload-aware benchmark of representative KV-cache optimization mechanisms spanning quantization, pruning, and merging, including KIVI, TurboQuant, SnapKV, and CaM, evaluated on LongBench-style multi-document QA, single-document QA, few-shot learning, and summarization workloads using Llama-3.1-8B-Instruct and Mistral-7B-Instruct-v0.3. The benchmark measures task quality, mean output throughput, mean time-to-first-token, and realized compression ratio across context-length buckets. The results show that the compression ratio alone is a poor predictor of end-to-end performance. KIVI4 provides the most stable quality across models, SnapKV delivers the strongest long-context throughput, and CaM yields large gains on selected QA workloads but exhibits substantial workload sensitivity in both quality and realized compression ratio. These findings motivate workload-aware selection of KV-cache mechanisms rather than one-size-fits-all compression and provide deployment guidance for long-context serving systems. △ Less

Submitted 3 May, 2026; originally announced July 2026.

SAFE-Cascade: Cost-Adaptive Vision-Language Routing for Chart Question Answering

Authors: Ayush Dwivedi, Qixin Wang, Ashvi Soni, Ruoteng Wang, Han Li, Animesh Mahapatra, Neeraj Agrawal, Xintao Wu

Abstract: Vision-language models (VLMs) are powerful for chart question answering, but invoking a VLM for every query can be unnecessarily expensive when many questions are answerable from OCR text and lightweight language reasoning. We demonstrate SAFE-Cascade, an interactive system for cost-adaptive chart question answering. Given a chart image and a natural-language question, SAFE-Cascade first extracts… ▽ More Vision-language models (VLMs) are powerful for chart question answering, but invoking a VLM for every query can be unnecessarily expensive when many questions are answerable from OCR text and lightweight language reasoning. We demonstrate SAFE-Cascade, an interactive system for cost-adaptive chart question answering. Given a chart image and a natural-language question, SAFE-Cascade first extracts chart text with OCR, obtains a provisional answer from a text-only language model, and then uses a learned router to decide whether to accept the text answer or escalate to a VLM. The demo exposes this decision process to users: OCR evidence, text-only answer, routing probability, escalation decision, final answer, estimated cost, and estimated latency are shown side by side. SAFE-Cascade is designed as a transparent interface for understanding when visual grounding is actually needed. Users can upload or select charts, ask questions, inspect the evidence used by each pathway, compare text-only and VLM answers, and adjust the escalation threshold to explore the accuracy-cost frontier. The system is implemented with Azure Document Intelligence for OCR, gpt-5-mini as the text-only model, gemini-2.5-flash-image as the VLM, and a Random Forest router trained on inference-time features. On a held-out ChartQA test split of 375 examples from a 2,500-example experiment, SAFE-Cascade achieves 69.1% unified accuracy with 73.1% VLM invocation, compared with 67.7% accuracy and 100% VLM invocation for the full-VLM baseline. The observed +1.4 percentage-point difference is statistically uncertain, so we interpret SAFE-Cascade as matching full-VLM performance while reducing VLM calls by 26.9% and estimated cost by 9.3%. The demonstration shows how selective modality routing can make multimodal knowledge systems more transparent, tunable, and cost-aware. △ Less

Submitted 17 June, 2026; originally announced June 2026.

Comments: Demo paper submitted at CIKM 2026. 4 pages, 2 figures

ACM Class: H.3.3; I.2.7

LLM-Based Intelligent Notification Composition: From Static Personalization to Context-Aware Persuasive Messaging

Authors: Nilesh Agrawal

Abstract: Push notifications remain among the most direct channels through which digital platforms engage users, yet existing approaches have invested heavily in who to notify, when to notify, and what to recommend, while leaving how to communicate as the least-optimized stage. This paper argues that message quality is an independent, underinvested lever, and that LLMs create their most differentiated value… ▽ More Push notifications remain among the most direct channels through which digital platforms engage users, yet existing approaches have invested heavily in who to notify, when to notify, and what to recommend, while leaving how to communicate as the least-optimized stage. This paper argues that message quality is an independent, underinvested lever, and that LLMs create their most differentiated value precisely at this layer. We make three contributions. First, we define notification message quality along six dimensions (contextual relevance, clarity, actionability, novelty handling, linguistic freshness, and persuasive appropriateness) and show how LLM-based composition improves each relative to templates. Across reviewed deployments, reported improvements range from +8% to +14.5% CTR over static templates and +1% to +2.5% over mature slot-filling systems, though these span heterogeneous systems and should not be treated as directly comparable. Second, we provide an architectural attribution analysis disentangling message generation from adjacent components (targeting, ranking, timing), arguing that observed gains are frequently misattributed to text generation alone. Third, we introduce a three-criterion decision framework specifying when LLM generation is and is not the binding constraint. We support these arguments through a PRISMA-guided survey (28 sources from 142 screened), examine domain-specific applications across social media, food delivery, and e-commerce, and propose a unified architectural framework with budget-aware routing, grounded generation, candidate ranking, diversity controls, and online learning. △ Less

Submitted 21 March, 2026; originally announced May 2026.

Comments: 17 pages, 1 figure, 7 tables. Code available at https://github.com/ndagrawal/LLMNotificationComposition

ACM Class: H.3.5; I.2.7

It's All Connected: Topology-Aware Structural Graph Encoding Improves Performance on Polymer Prediction

Authors: H. Ibrahim Erdogan, Punith Raviswamy, Nikita Agrawal, Yannik Köster, Stefan Zechel, Ulrich S. Schubert, Ruben Mayer, Christopher Kuenneth

Abstract: Graph Neural Networks (GNNs) have achieved strong results in molecular property prediction, but polymers present distinct challenges: labeled datasets are scarce and small (typically in the order of hundreds of polymers) due to the need for expensive experimentation, and complex polymer chain distributions influence polymer properties. Established practice in polymer prediction represents polymers… ▽ More Graph Neural Networks (GNNs) have achieved strong results in molecular property prediction, but polymers present distinct challenges: labeled datasets are scarce and small (typically in the order of hundreds of polymers) due to the need for expensive experimentation, and complex polymer chain distributions influence polymer properties. Established practice in polymer prediction represents polymers solely by graphs of their repeat units, discarding the chain-scale morphology that governs key properties such as the glass transition temperature ($T_g$). In this work, we propose a principled graph construction that addresses this gap. Given a polymer's molecular mass distribution (MMD), we sample representative chains from the Schulz-Zimm distribution and construct representative sets of large graphs encoding chain-scale topology directly, with atoms and bonds featurized using rich chemical descriptors. We further pretrain GNN encoders via masked graph modeling on 100,000 unlabeled PSMILES strings before fine-tuning on labeled data. On a dataset of 381 polymers (180 homopolymers and 201 copolymers), we show that graph construction and self-supervised pretraining are jointly necessary: without pretraining, the large graph method matches the repeat-unit baseline (28.40 K vs. 28.36 K RMSE); with pretraining, it achieves 24.76 K +/- 3.30 K, a 5.1% reduction in mean error over the pretrained repeat-unit baseline (26.08 K +/- 4.20 K, p < 0.001, 30 runs). An ablation removing chemical features degrades performance to 36.65 K, confirming both components are essential. Results are architecture-agnostic, holding for both GINE and GATv2 encoders. △ Less

Submitted 11 May, 2026; originally announced May 2026.

Comments: 9 pages, 4 figures

ACM Class: I.2.6; J.2

Financial Bond Similarity Search Using Representation Learning

Authors: Amin Haeri, Mahdi Ghelichi, Nishant Agrawal, David Li, Catalina Gomez Sanchez

Abstract: Finding similar bonds remains challenging in fixed-income analytics, as numerical financial attributes often overshadow categorical non-financial ones such as issuer sector and domicile. This paper shows that these categorical attributes dominate the predictability of spread curves and proposes embedding models to capture their semantic similarities, outperforming one-hot and many other baselines.… ▽ More Finding similar bonds remains challenging in fixed-income analytics, as numerical financial attributes often overshadow categorical non-financial ones such as issuer sector and domicile. This paper shows that these categorical attributes dominate the predictability of spread curves and proposes embedding models to capture their semantic similarities, outperforming one-hot and many other baselines. Evaluated via sparse-issuer augmentation, the approach improves risk modeling and curve construction. △ Less

Submitted 1 February, 2026; originally announced February 2026.

Comments: 22 pages, 18 figures, 1 table

Phase-Aware Deep Learning with Complex-Valued CNNs for Audio Signal Applications

Authors: Naman Agrawal

Abstract: This study explores the design and application of Complex-Valued Convolutional Neural Networks (CVCNNs) in audio signal processing, with a focus on preserving and utilizing phase information often neglected in real-valued networks. We begin by presenting the foundational theoretical concepts of CVCNNs, including complex convolutions, pooling layers, Wirtinger-based differentiation, and various com… ▽ More This study explores the design and application of Complex-Valued Convolutional Neural Networks (CVCNNs) in audio signal processing, with a focus on preserving and utilizing phase information often neglected in real-valued networks. We begin by presenting the foundational theoretical concepts of CVCNNs, including complex convolutions, pooling layers, Wirtinger-based differentiation, and various complex-valued activation functions. These are complemented by critical adaptations of training techniques, including complex batch normalization and weight initialization schemes, to ensure stability in training dynamics. Empirical evaluations are conducted across three stages. First, CVCNNs are benchmarked on standard image datasets, where they demonstrate competitive performance with real-valued CNNs, even under synthetic complex perturbations. Although our focus is audio signal processing, we first evaluate CVCNNs on image datasets to establish baseline performance and validate training stability before applying them to audio tasks. In the second experiment, we focus on audio classification using Mel-Frequency Cepstral Coefficients (MFCCs). CVCNNs trained on real-valued MFCCs slightly outperform real CNNs, while preserving phase in input workflows highlights challenges in exploiting phase without architectural modifications. Finally, a third experiment introduces GNNs to model phase information via edge weighting, where the inclusion of phase yields measurable gains in both binary and multi-class genre classification. These results underscore the expressive capacity of complex-valued architectures and confirm phase as a meaningful and exploitable feature in audio processing applications. While current methods show promise, especially with activations like cardioid, future advances in phase-aware design will be essential to leverage the potential of complex representations in neural networks. △ Less

Submitted 10 October, 2025; originally announced October 2025.

Re:Verse -- Can Your VLM Read a Manga?

Authors: Aaditya Baranwal, Madhav Kataria, Naitik Agrawal, Yogesh S Rawat, Shruti Vyas

Abstract: Current Vision Language Models (VLMs) demonstrate a critical gap between surface-level recognition and deep narrative reasoning when processing sequential visual storytelling. Through a comprehensive investigation of manga narrative understanding, we reveal that while recent large multimodal models excel at individual panel interpretation, they systematically fail at temporal causality and cross-p… ▽ More Current Vision Language Models (VLMs) demonstrate a critical gap between surface-level recognition and deep narrative reasoning when processing sequential visual storytelling. Through a comprehensive investigation of manga narrative understanding, we reveal that while recent large multimodal models excel at individual panel interpretation, they systematically fail at temporal causality and cross-panel cohesion, core requirements for coherent story comprehension. We introduce a novel evaluation framework that combines fine-grained multimodal annotation, cross-modal embedding analysis, and retrieval-augmented assessment to systematically characterize these limitations. Our methodology includes (i) a rigorous annotation protocol linking visual elements to narrative structure through aligned light novel text, (ii) comprehensive evaluation across multiple reasoning paradigms, including direct inference and retrieval-augmented generation, and (iii) cross-modal similarity analysis revealing fundamental misalignments in current VLMs' joint representations. Applying this framework to Re:Zero manga across 11 chapters with 308 annotated panels, we conduct the first systematic study of long-form narrative understanding in VLMs through three core evaluation axes: generative storytelling, contextual dialogue grounding, and temporal reasoning. Our findings demonstrate that current models lack genuine story-level intelligence, struggling particularly with non-linear narratives, character consistency, and causal inference across extended sequences. This work establishes both the foundation and practical methodology for evaluating narrative intelligence, while providing actionable insights into the capability of deep sequential understanding of Discrete Visual Narratives beyond basic recognition in Multimodal Models. Project Page: https://re-verse.vercel.app △ Less

Submitted 18 August, 2025; v1 submitted 11 August, 2025; originally announced August 2025.

Comments: Accepted (oral) at ICCV (AISTORY Workshop) 2025

Journal ref: 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), pp. 3820-3830

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Authors: Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, Luke Marris, Sam Petulla, Colin Gaffney, Asaf Aharoni, Nathan Lintz, Tiago Cardal Pais, Henrik Jacobsson, Idan Szpektor, Nan-Jiang Jiang, Krishna Haridasan, Ahmed Omran, Nikunj Saunshi, Dara Bahri, Gaurav Mishra, Eric Chu , et al. (3410 additional authors not shown)

Abstract: In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal unde… ▽ More In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving. △ Less

Submitted 19 December, 2025; v1 submitted 7 July, 2025; originally announced July 2025.

Comments: 72 pages, 17 figures

Building a Few-Shot Cross-Domain Multilingual NLU Model for Customer Care

Authors: Saurabh Kumar, Sourav Bansal, Neeraj Agrawal, Priyanka Bhatt

Abstract: Customer care is an essential pillar of the e-commerce shopping experience with companies spending millions of dollars each year, employing automation and human agents, across geographies (like US, Canada, Mexico, Chile), channels (like Chat, Interactive Voice Response (IVR)), and languages (like English, Spanish). SOTA pre-trained models like multilingual-BERT, fine-tuned on annotated data have s… ▽ More Customer care is an essential pillar of the e-commerce shopping experience with companies spending millions of dollars each year, employing automation and human agents, across geographies (like US, Canada, Mexico, Chile), channels (like Chat, Interactive Voice Response (IVR)), and languages (like English, Spanish). SOTA pre-trained models like multilingual-BERT, fine-tuned on annotated data have shown good performance in downstream tasks relevant to Customer Care. However, model performance is largely subject to the availability of sufficient annotated domain-specific data. Cross-domain availability of data remains a bottleneck, thus building an intent classifier that generalizes across domains (defined by channel, geography, and language) with only a few annotations, is of great practical value. In this paper, we propose an embedder-cum-classifier model architecture which extends state-of-the-art domain-specific models to other domains with only a few labeled samples. We adopt a supervised fine-tuning approach with isotropic regularizers to train a domain-specific sentence embedder and a multilingual knowledge distillation strategy to generalize this embedder across multiple domains. The trained embedder, further augmented with a simple linear classifier can be deployed for new domains. Experiments on Canada and Mexico e-commerce Customer Care dataset with few-shot intent detection show an increase in accuracy by 20-23% against the existing state-of-the-art pre-trained models. △ Less

Submitted 4 June, 2025; originally announced June 2025.

Journal ref: ECAI 2023. IOS Press, 2023. 3212-3217

Hierarchical Text Classification Using Contrastive Learning Informed Path Guided Hierarchy

Authors: Neeraj Agrawal, Saurabh Kumar, Priyanka Bhatt, Tanishka Agarwal

Abstract: Hierarchical Text Classification (HTC) has recently gained traction given the ability to handle complex label hierarchy. This has found applications in domains like E- commerce, customer care and medicine industry among other real-world applications. Existing HTC models either encode label hierarchy separately and mix it with text encoding or guide the label hierarchy structure in the text encoder… ▽ More Hierarchical Text Classification (HTC) has recently gained traction given the ability to handle complex label hierarchy. This has found applications in domains like E- commerce, customer care and medicine industry among other real-world applications. Existing HTC models either encode label hierarchy separately and mix it with text encoding or guide the label hierarchy structure in the text encoder. Both approaches capture different characteristics of label hierarchy and are complementary to each other. In this paper, we propose a Hierarchical Text Classification using Contrastive Learning Informed Path guided hierarchy (HTC-CLIP), which learns hierarchy-aware text representation and text informed path guided hierarchy representation using contrastive learning. During the training of HTC-CLIP, we learn two different sets of class probabilities distributions and during inference, we use the pooled output of both probabilities for each class to get the best of both representations. Our results show that the two previous approaches can be effectively combined into one architecture to achieve improved performance. Tests on two public benchmark datasets showed an improvement of 0.99 - 2.37% in Macro F1 score using HTC-CLIP over the existing state-of-the-art models. △ Less

Submitted 4 June, 2025; originally announced June 2025.

Comments: arXiv admin note: text overlap with arXiv:2203.03825 by other authors

Journal ref: ECAI 2023, pp. 19-26. IOS Press, 2023

Enhancing Customer Service Chatbots with Context-Aware NLU through Selective Attention and Multi-task Learning

Authors: Subhadip Nandi, Neeraj Agrawal, Anshika Singh, Priyanka Bhatt

Abstract: Customer service chatbots are conversational systems aimed at addressing customer queries, often by directing them to automated workflows. A crucial aspect of this process is the classification of the customer's intent. Presently, most intent classification models for customer care utilise only customer query for intent prediction. This may result in low-accuracy models, which cannot handle ambigu… ▽ More Customer service chatbots are conversational systems aimed at addressing customer queries, often by directing them to automated workflows. A crucial aspect of this process is the classification of the customer's intent. Presently, most intent classification models for customer care utilise only customer query for intent prediction. This may result in low-accuracy models, which cannot handle ambiguous queries. An ambiguous query like "I didn't receive my package" could indicate a delayed order, or an order that was delivered but the customer failed to receive it. Resolution of each of these scenarios requires the execution of very different sequence of steps. Utilizing additional information, such as the customer's order delivery status, in the right manner can help identify the intent for such ambiguous queries. In this paper, we have introduced a context-aware NLU model that incorporates both, the customer query and contextual information from the customer's order status for predicting customer intent. A novel selective attention module is used to extract relevant context features. We have also proposed a multi-task learning paradigm for the effective utilization of different label types available in our training data. Our suggested method, Multi-Task Learning Contextual NLU with Selective Attention Weighted Context (MTL-CNLU-SAWC), yields a 4.8% increase in top 2 accuracy score over the baseline model which only uses user queries, and a 3.5% improvement over existing state-of-the-art models that combine query and context. We have deployed our model to production for Walmart's customer care domain. Accurate intent prediction through MTL-CNLU-SAWC helps to better direct customers to automated workflows, thereby significantly reducing escalations to human agents, leading to almost a million dollars in yearly savings for the company. △ Less

Submitted 2 June, 2025; originally announced June 2025.

Journal ref: CODS-COMAD Dec '24: 8th International Conference on Data Science and Management of Data (12th ACM IKDD CODS and 30th COMAD), Jodhpur, India, December 2024

Federated Foundation Language Model Post-Training Should Focus on Open-Source Models

Authors: Nikita Agrawal, Ruben Mayer

Abstract: Post-training of foundation language models has emerged as a promising research domain in federated learning (FL) with the goal to enable privacy-preserving model improvements and adaptations to user's downstream tasks. Recent advances in this area adopt centralized post-training approaches that build upon black-box foundation language models where there is no access to model weights and architect… ▽ More Post-training of foundation language models has emerged as a promising research domain in federated learning (FL) with the goal to enable privacy-preserving model improvements and adaptations to user's downstream tasks. Recent advances in this area adopt centralized post-training approaches that build upon black-box foundation language models where there is no access to model weights and architecture details. Although the use of black-box models has been successful in centralized post-training, their blind replication in FL raises several concerns. Our opinion is that using black-box models in FL contradicts the core principles of federation such as data privacy and autonomy. In this paper, we critically analyze the usage of black-box models in federated post-training, and provide a detailed account of various aspects of openness and their implications for FL. △ Less

Submitted 14 June, 2026; v1 submitted 29 May, 2025; originally announced May 2025.

Comments: Accepted at International Workshop on Federated Learning in the Age of Foundation Models In Conjunction with IJCAI 2026

Spoken Language Understanding on Unseen Tasks With In-Context Learning

Authors: Neeraj Agrawal, Sriram Ganapathy

Abstract: Spoken language understanding (SLU) tasks involve diverse skills that probe the information extraction, classification and/or generation capabilities of models. In this setting, task-specific training data may not always be available. While traditional task-specific SLU models are unable to cater to such requirements, the speech-text large language models (LLMs) offer a promising alternative with… ▽ More Spoken language understanding (SLU) tasks involve diverse skills that probe the information extraction, classification and/or generation capabilities of models. In this setting, task-specific training data may not always be available. While traditional task-specific SLU models are unable to cater to such requirements, the speech-text large language models (LLMs) offer a promising alternative with emergent abilities. However, out of-the-box, our evaluations indicate that the zero/few-shot performance of prominent open-source speech-text LLMs on SLU tasks are not up to the mark. In this paper, we introduce a novel approach to robust task-agnostic fine-tuning using randomized class labels. With this proposed fine-tuning, we illustrate that the performance of the speech-text LLMs on an unseen task is significantly improved over standard approaches. Critically, the proposed approach avoids the requirement of task-specific data annotations for enabling new tasks in speech-text LLMs. △ Less

Submitted 12 May, 2025; originally announced May 2025.

Journal ref: Proc. Interspeech 2025, 4103-4107

AI-Enabled Conversational Journaling for Advancing Parkinson's Disease Symptom Tracking

Authors: Mashrur Rashik, Shilpa Sweth, Nishtha Agrawal, Saiyyam Kochar, Kara M Smith, Fateme Rajabiyazdi, Vidya Setlur, Narges Mahyar, Ali Sarvghad

Abstract: Journaling plays a crucial role in managing chronic conditions by allowing patients to document symptoms and medication intake, providing essential data for long-term care. While valuable, traditional journaling methods often rely on static, self-directed entries, lacking interactive feedback and real-time guidance. This gap can result in incomplete or imprecise information, limiting its usefulnes… ▽ More Journaling plays a crucial role in managing chronic conditions by allowing patients to document symptoms and medication intake, providing essential data for long-term care. While valuable, traditional journaling methods often rely on static, self-directed entries, lacking interactive feedback and real-time guidance. This gap can result in incomplete or imprecise information, limiting its usefulness for effective treatment. To address this gap, we introduce PATRIKA, an AI-enabled prototype designed specifically for people with Parkinson's disease (PwPD). The system incorporates cooperative conversation principles, clinical interview simulations, and personalization to create a more effective and user-friendly journaling experience. Through two user studies with PwPD and iterative refinement of PATRIKA, we demonstrate conversational journaling's significant potential in patient engagement and collecting clinically valuable information. Our results showed that generating probing questions PATRIKA turned journaling into a bi-directional interaction. Additionally, we offer insights for designing journaling systems for healthcare and future directions for promoting sustained journaling. △ Less

Submitted 5 March, 2025; originally announced March 2025.

Comments: To appear in the ACM CHI conference on Human Factors in Computing Systems (CHI), 2025

CRUPL: A Semi-Supervised Cyber Attack Detection with Consistency Regularization and Uncertainty-aware Pseudo-Labeling in Smart Grid

Authors: Smruti P. Dash, Kedar V. Khandeparkar, Nipun Agrawal

Abstract: The modern power grids are integrated with digital technologies and automation systems. The inclusion of digital technologies has made the smart grids vulnerable to cyber-attacks. Cyberattacks on smart grids can compromise data integrity and jeopardize the reliability of the power supply. Traditional intrusion detection systems often need help to effectively detect novel and sophisticated attacks… ▽ More The modern power grids are integrated with digital technologies and automation systems. The inclusion of digital technologies has made the smart grids vulnerable to cyber-attacks. Cyberattacks on smart grids can compromise data integrity and jeopardize the reliability of the power supply. Traditional intrusion detection systems often need help to effectively detect novel and sophisticated attacks due to their reliance on labeled training data, which may only encompass part of the spectrum of potential threats. This work proposes a semi-supervised method for cyber-attack detection in smart grids by leveraging the labeled and unlabeled measurement data. We implement consistency regularization and pseudo-labeling to identify deviations from expected behavior and predict the attack classes. We use a curriculum learning approach to improve pseudo-labeling performance, capturing the model uncertainty. We demonstrate the efficiency of the proposed method in detecting different types of cyberattacks, minimizing the false positives by implementing them on publicly available datasets. The method proposes a promising solution by improving the detection accuracy to 99% in the presence of unknown samples and significantly reducing false positives. △ Less

Submitted 1 March, 2025; originally announced March 2025.

Comments: 20 pages, 5 figures

MSC Class: 68T07 (Primary); 68T27; 68T37 (Secondary) ACM Class: I.2.m

Pause-Tuning for Long-Context Comprehension: A Lightweight Approach to LLM Attention Recalibration

Authors: James Begin, Namit Agrawal, Eshan Singh, Yicheng Fu, Sean O'Brien, Vasu Sharma, Kevin Zhu

Abstract: LLMs have demonstrated remarkable proficiency in understanding tasks but continue to struggle with long-context comprehension, particularly with content located in the middle of extensive inputs. This limitation, known as the Lost-in-the-Middle (LITM) problem, hinders models from fully processing and utilizing information across lengthy contexts. To address this issue, we introduce pause-tuning, a… ▽ More LLMs have demonstrated remarkable proficiency in understanding tasks but continue to struggle with long-context comprehension, particularly with content located in the middle of extensive inputs. This limitation, known as the Lost-in-the-Middle (LITM) problem, hinders models from fully processing and utilizing information across lengthy contexts. To address this issue, we introduce pause-tuning, a technique that redistributes attention to enhance comprehension of long-context inputs. Our approach involves fine-tuning language models on datasets with artificially inserted pause tokens, which serve to segment the input into smaller, more manageable parts. We evaluate pause-tuning against alternative approaches using the Needle-in-a-Haystack benchmark, where models must retrieve information embedded within contexts of up to 128K tokens. Experimental results demonstrate significant performance gains, with the LLaMA 3.2 3B Instruct model and the LLaMA 3.1 8B Instruct model improving by 10.61% and 3.57% respectively on average, suggesting that pause-tuning successfully enhances attention redistribution and improves long-context retention. The code and data are available at https://anonymous.4open.science/r/LITM-PauseTokens-7357. △ Less

Submitted 1 February, 2025; originally announced February 2025.

Understanding Museum Exhibits using Vision-Language Reasoning

Authors: Ada-Astrid Balauca, Sanjana Garai, Stefan Balauca, Rasesh Udayakumar Shetty, Naitik Agrawal, Dhwanil Subhashbhai Shah, Yuqian Fu, Xi Wang, Kristina Toutanova, Danda Pani Paudel, Luc Van Gool

Abstract: Museums serve as repositories of cultural heritage and historical artifacts from diverse epochs, civilizations, and regions, preserving well-documented collections that encapsulate vast knowledge, which, when systematically structured into large-scale datasets, can train specialized models. Visitors engage with exhibits through curiosity and questions, making expert domain-specific models essentia… ▽ More Museums serve as repositories of cultural heritage and historical artifacts from diverse epochs, civilizations, and regions, preserving well-documented collections that encapsulate vast knowledge, which, when systematically structured into large-scale datasets, can train specialized models. Visitors engage with exhibits through curiosity and questions, making expert domain-specific models essential for interactive query resolution and gaining historical insights. Understanding exhibits from images requires analyzing visual features and linking them to historical knowledge to derive meaningful correlations. We facilitate such reasoning by (a) collecting and curating a large-scale dataset of 65M images and 200M question-answer pairs for exhibits from all around the world; (b) training large vision-language models (VLMs) on the collected dataset; (c) benchmarking their ability on five visual question answering tasks, specifically designed to reflect real-world inquiries and challenges observed in museum settings. The complete dataset is labeled by museum experts, ensuring the quality and the practical significance of the labels. We train two VLMs from different categories: BLIP with vision-language aligned embeddings, but lacking the expressive power of large language models, and the LLaVA model, a powerful instruction-tuned LLM enriched with vision-language reasoning capabilities. Through extensive experiments, we find that while both model types effectively answer visually grounded questions, large vision-language models excel in queries requiring deeper historical context and reasoning. We further demonstrate the necessity of fine-tuning models on large-scale domain-specific datasets by showing that our fine-tuned models significantly outperform current SOTA VLMs in answering questions related to specific attributes, highlighting their limitations in handling complex, nuanced queries. △ Less

Submitted 8 September, 2025; v1 submitted 2 December, 2024; originally announced December 2024.

Comments: Accepted at ICCV 2025

Improving Few-Shot Cross-Domain Named Entity Recognition by Instruction Tuning a Word-Embedding based Retrieval Augmented Large Language Model

Authors: Subhadip Nandi, Neeraj Agrawal

Abstract: Few-Shot Cross-Domain NER is the process of leveraging knowledge from data-rich source domains to perform entity recognition on data scarce target domains. Most previous state-of-the-art (SOTA) approaches use pre-trained language models (PLMs) for cross-domain NER. However, these models are often domain specific. To successfully use these models for new target domains, we need to modify either the… ▽ More Few-Shot Cross-Domain NER is the process of leveraging knowledge from data-rich source domains to perform entity recognition on data scarce target domains. Most previous state-of-the-art (SOTA) approaches use pre-trained language models (PLMs) for cross-domain NER. However, these models are often domain specific. To successfully use these models for new target domains, we need to modify either the model architecture or perform model finetuning using data from the new domains. Both of these result in the creation of entirely new NER models for each target domain which is infeasible for practical scenarios. Recently,several works have attempted to use LLMs to solve Few-Shot Cross-Domain NER. However, most of these are either too expensive for practical purposes or struggle to follow LLM prompt instructions. In this paper, we propose IF-WRANER (Instruction Finetuned Word-embedding based Retrieval Augmented large language model for Named Entity Recognition), a retrieval augmented LLM, finetuned for the NER task. By virtue of the regularization techniques used during LLM finetuning and the adoption of word-level embedding over sentence-level embedding during the retrieval of in-prompt examples, IF-WRANER is able to outperform previous SOTA Few-Shot Cross-Domain NER approaches. We have demonstrated the effectiveness of our model by benchmarking its performance on the open source CrossNER dataset, on which it shows more than 2% F1 score improvement over the previous SOTA model. We have deployed the model for multiple customer care domains of an enterprise. Accurate entity prediction through IF-WRANER helps direct customers to automated workflows for the domains, thereby reducing escalations to human agents by almost 15% and leading to millions of dollars in yearly savings for the company. △ Less

Submitted 1 November, 2024; originally announced November 2024.

Report number: 2024.emnlp-industry.51

Journal ref: Proceedings of the 2024 Conference on EMNLP Industry Track pages 686,696

Towards Bridging the Gap between Near and Far-Field Characterizations of the Wireless Channel

Authors: Navneet Agrawal, Ehsan Tohidi, Renato L. G. Cavalcante, Sławomir Stańczak

Abstract: The "near-field" propagation modeling of wireless channels is necessary to support sixth-generation (6G) technologies, such as intelligent reflecting surface (IRS), that are enabled by large aperture antennas and higher frequency carriers. As the conventional far-field model proves inadequate in this context, there is a pressing need to explore and bridge the gap between near and far-field propaga… ▽ More The "near-field" propagation modeling of wireless channels is necessary to support sixth-generation (6G) technologies, such as intelligent reflecting surface (IRS), that are enabled by large aperture antennas and higher frequency carriers. As the conventional far-field model proves inadequate in this context, there is a pressing need to explore and bridge the gap between near and far-field propagation models. Although far-field models are simple and provide computationally efficient solutions for many practical applications, near-field models provide the most accurate representation of wireless channels. This paper builds upon the foundations of electromagnetic wave propagation theory to derive near and far-field models as approximations of the Green's function (Maxwell's equations). We characterize the near and far-field models both theoretically and with the help of simulations in a line-of-sight (LOS)-only scenario. In particular, for two key applications in multiantenna systems, namely, beamforming and multiple-access, we showcase the advantages of using the near-field model over the far-field, and present a novel scheduling scheme for multiple-access in the near-field regime. Our findings offer insights into the challenge of incorporating near-field models in practical wireless systems, fostering enhanced performance in future communication technologies. △ Less

Submitted 10 March, 2024; v1 submitted 26 February, 2024; originally announced February 2024.

Comments: Published at IEEE International Conference on Communications (ICC) 2024. IEEE Copyright protected

Distributed fixed-point algorithms for dynamic convex optimization over decentralized and unbalanced wireless networks

Authors: Navneet Agrawal, Renato L. G. Cavalcante, Sławomir Stańczak

Abstract: We consider problems where agents in a network seek a common quantity, measured independently and periodically by each agent through a local time-varying process. Numerous solvers addressing such problems have been developed in the past, featuring various adaptations of the local processing and the consensus step. However, existing solvers still lack support for advanced techniques, such as superi… ▽ More We consider problems where agents in a network seek a common quantity, measured independently and periodically by each agent through a local time-varying process. Numerous solvers addressing such problems have been developed in the past, featuring various adaptations of the local processing and the consensus step. However, existing solvers still lack support for advanced techniques, such as superiorization and over-the-air function computation (OTA-C). To address this limitation, we introduce a comprehensive framework for the analysis of distributed algorithms by characterizing them using the quasi-Fejér type algorithms and an extensive communication model. Under weak assumptions, we prove almost sure convergence of the algorithm to a common estimate for all agents. Moreover, we develop a specific class of algorithms within this framework to tackle distributed optimization problems with time-varying objectives, and, assuming that a time-invariant solution exists, prove its convergence to a solution. We also present a novel OTA-C protocol for consensus step in large decentralized networks, reducing communication overhead and enhancing network autonomy as compared to the existing protocols. The effectiveness of the algorithm, featuring superiorization and OTA-C, is demonstrated in a real-world application of distributed supervised learning over time-varying wireless networks, highlighting its low-latency and energy-efficiency compared to standard approaches. △ Less

Submitted 4 March, 2024; v1 submitted 31 January, 2024; originally announced January 2024.

Comments: Published at: 27th International Workshop on Smart Antennas (WSA) 2024, Dresden, Germany. Copyright: IEEE 2024

No prejudice! Fair Federated Graph Neural Networks for Personalized Recommendation

Authors: Nimesh Agrawal, Anuj Kumar Sirohi, Jayadeva, Sandeep Kumar

Abstract: Ensuring fairness in Recommendation Systems (RSs) across demographic groups is critical due to the increased integration of RSs in applications such as personalized healthcare, finance, and e-commerce. Graph-based RSs play a crucial role in capturing intricate higher-order interactions among entities. However, integrating these graph models into the Federated Learning (FL) paradigm with fairness c… ▽ More Ensuring fairness in Recommendation Systems (RSs) across demographic groups is critical due to the increased integration of RSs in applications such as personalized healthcare, finance, and e-commerce. Graph-based RSs play a crucial role in capturing intricate higher-order interactions among entities. However, integrating these graph models into the Federated Learning (FL) paradigm with fairness constraints poses formidable challenges as this requires access to the entire interaction graph and sensitive user information (such as gender, age, etc.) at the central server. This paper addresses the pervasive issue of inherent bias within RSs for different demographic groups without compromising the privacy of sensitive user attributes in FL environment with the graph-based model. To address the group bias, we propose F2PGNN (Fair Federated Personalized Graph Neural Network), a novel framework that leverages the power of Personalized Graph Neural Network (GNN) coupled with fairness considerations. Additionally, we use differential privacy techniques to fortify privacy protection. Experimental evaluation on three publicly available datasets showcases the efficacy of F2PGNN in mitigating group unfairness by 47% - 99% compared to the state-of-the-art while preserving privacy and maintaining the utility. The results validate the significance of our framework in achieving equitable and personalized recommendations using GNN within the FL landscape. △ Less

Submitted 20 December, 2023; v1 submitted 10 December, 2023; originally announced December 2023.

Comments: To appear as a full paper in AAAI 2024

Libertas: Privacy-Preserving Collective Computation for Decentralised Personal Data Stores

Authors: Rui Zhao, Naman Goel, Nitin Agrawal, Jun Zhao, Jake Stein, Wael Albayaydh, Ruben Verborgh, Reuben Binns, Tim Berners-Lee, Nigel Shadbolt

Abstract: Data and data processing have become an indispensable aspect for our society. Insights drawn from collective data make invaluable contribution to scientific and societal research and business. But there are increasing worries about privacy issues and data misuse. This has prompted the emergence of decentralised personal data stores (PDS) like Solid that provide individuals more control over their… ▽ More Data and data processing have become an indispensable aspect for our society. Insights drawn from collective data make invaluable contribution to scientific and societal research and business. But there are increasing worries about privacy issues and data misuse. This has prompted the emergence of decentralised personal data stores (PDS) like Solid that provide individuals more control over their personal data. However, existing PDS frameworks face challenges in ensuring data privacy when performing collective computations with data from multiple users. While Secure Multi-Party Computation (MPC) offers input secrecy protection during the computation without relying on any single party, issues emerge when directly applying MPC in the context of PDS, particularly due to key factors like autonomy and decentralisation. In this work, we discuss the essence of this issue, identify a potential solution, and introduce a modular architecture, Libertas, to integrate MPC with PDS like Solid, without requiring protocol-level changes. We introduce a paradigm shift from an `omniscient' view to individual-based, user-centric view of trust and security, and discuss the threat model of Libertas. Two realistic use cases for collaborative data processing are used for evaluation, both for technical feasibility and empirical benchmark, highlighting its effectiveness in empowering gig workers and generating differentially private synthetic data. The results of our experiments underscore Libertas' linear scalability and provide valuable insights into compute optimisations, thereby advancing the state-of-the-art in privacy-preserving data processing practices. By offering practical solutions for maintaining both individual autonomy and privacy in collaborative data processing environments, Libertas contributes significantly to the ongoing discourse on privacy protection in data-driven decision-making contexts. △ Less

Submitted 30 March, 2025; v1 submitted 28 September, 2023; originally announced September 2023.

Comments: Accepted by CSCW 2025; manuscript version

Coded Distributed Image Classification

Authors: Jiepeng Tang, Navneet Agrawal, Slawomir Stanczak, Jingge Zhu

Abstract: In this paper, we present a coded computation (CC) scheme for distributed computation of the inference phase of machine learning (ML) tasks, specifically, the task of image classification. Building upon Agrawal et al.~2022, the proposed scheme combines the strengths of deep learning and Lagrange interpolation technique to mitigate the effect of straggling workers, and recovers approximate results… ▽ More In this paper, we present a coded computation (CC) scheme for distributed computation of the inference phase of machine learning (ML) tasks, specifically, the task of image classification. Building upon Agrawal et al.~2022, the proposed scheme combines the strengths of deep learning and Lagrange interpolation technique to mitigate the effect of straggling workers, and recovers approximate results with reasonable accuracy using outputs from any $R$ out of $N$ workers, where $R\leq N$. Our proposed scheme guarantees a minimum recovery threshold $R$ for non-polynomial problems, which can be adjusted as a tunable parameter in the system. Moreover, unlike existing schemes, our scheme maintains flexibility with respect to worker availability and system design. We propose two system designs for our CC scheme that allows flexibility in distributing the computational load between the master and the workers based on the accessibility of input data. Our experimental results demonstrate the superiority of our scheme compared to the state-of-the-art CC schemes for image classification tasks, and pave the path for designing new schemes for distributed computation of any general ML classification tasks. △ Less

Submitted 10 July, 2023; originally announced July 2023.

Distributed Convex Optimization "Over-the-Air" in Dynamic Environments

Authors: Navneet Agrawal, Renato L. G. Cavalcante, Masahiro Yukawa, Slawomir Stanczak

Abstract: This paper presents a decentralized algorithm for solving distributed convex optimization problems in dynamic networks with time-varying objectives. The unique feature of the algorithm lies in its ability to accommodate a wide range of communication systems, including previously unsupported ones, by abstractly modeling the information exchange in the network. Specifically, it supports a novel comm… ▽ More This paper presents a decentralized algorithm for solving distributed convex optimization problems in dynamic networks with time-varying objectives. The unique feature of the algorithm lies in its ability to accommodate a wide range of communication systems, including previously unsupported ones, by abstractly modeling the information exchange in the network. Specifically, it supports a novel communication protocol based on the "over-the-air" function computation (OTA-C) technology, that is designed for an efficient and truly decentralized implementation of the consensus step of the algorithm. Unlike existing OTA-C protocols, the proposed protocol does not require the knowledge of network graph structure or channel state information, making it particularly suitable for decentralized implementation over ultra-dense wireless networks with time-varying topologies and fading channels. Furthermore, the proposed algorithm synergizes with the "superiorization" methodology, allowing the development of new distributed algorithms with enhanced performance for the intended applications. The theoretical analysis establishes sufficient conditions for almost sure convergence of the algorithm to a common time-invariant solution for all agents, assuming such a solution exists. Our algorithm is applied to a real-world distributed random field estimation problem, showcasing its efficacy in terms of convergence speed, scalability, and spectral efficiency. Furthermore, we present a superiorized version of our algorithm that achieves faster convergence with significantly reduced energy consumption compared to the unsuperiorized algorithm. △ Less

Submitted 10 July, 2023; originally announced July 2023.

Comments: Submitted to: IEEE Transactions on Signal and Information Processing over Networks

Free Lunch for Privacy Preserving Distributed Graph Learning

Authors: Nimesh Agrawal, Nikita Malik, Sandeep Kumar

Abstract: Learning on graphs is becoming prevalent in a wide range of applications including social networks, robotics, communication, medicine, etc. These datasets belonging to entities often contain critical private information. The utilization of data for graph learning applications is hampered by the growing privacy concerns from users on data sharing. Existing privacy-preserving methods pre-process the… ▽ More Learning on graphs is becoming prevalent in a wide range of applications including social networks, robotics, communication, medicine, etc. These datasets belonging to entities often contain critical private information. The utilization of data for graph learning applications is hampered by the growing privacy concerns from users on data sharing. Existing privacy-preserving methods pre-process the data to extract user-side features, and only these features are used for subsequent learning. Unfortunately, these methods are vulnerable to adversarial attacks to infer private attributes. We present a novel privacy-respecting framework for distributed graph learning and graph-based machine learning. In order to perform graph learning and other downstream tasks on the server side, this framework aims to learn features as well as distances without requiring actual features while preserving the original structural properties of the raw data. The proposed framework is quite generic and highly adaptable. We demonstrate the utility of the Euclidean space, but it can be applied with any existing method of distance approximation and graph learning for the relevant spaces. Through extensive experimentation on both synthetic and real datasets, we demonstrate the efficacy of the framework in terms of comparing the results obtained without data sharing to those obtained with data sharing as a benchmark. This is, to our knowledge, the first privacy-preserving distributed graph learning framework. △ Less

Submitted 19 May, 2023; v1 submitted 18 May, 2023; originally announced May 2023.

VeLO: Training Versatile Learned Optimizers by Scaling Up

Authors: Luke Metz, James Harrison, C. Daniel Freeman, Amil Merchant, Lucas Beyer, James Bradbury, Naman Agrawal, Ben Poole, Igor Mordatch, Adam Roberts, Jascha Sohl-Dickstein

Abstract: While deep learning models have replaced hand-designed features across many domains, these models are still trained with hand-designed optimizers. In this work, we leverage the same scaling approach behind the success of deep learning to learn versatile optimizers. We train an optimizer for deep learning which is itself a small neural network that ingests gradients and outputs parameter updates. M… ▽ More While deep learning models have replaced hand-designed features across many domains, these models are still trained with hand-designed optimizers. In this work, we leverage the same scaling approach behind the success of deep learning to learn versatile optimizers. We train an optimizer for deep learning which is itself a small neural network that ingests gradients and outputs parameter updates. Meta-trained with approximately four thousand TPU-months of compute on a wide variety of optimization tasks, our optimizer not only exhibits compelling performance, but optimizes in interesting and unexpected ways. It requires no hyperparameter tuning, instead automatically adapting to the specifics of the problem being optimized. We open source our learned optimizer, meta-training code, the associated train and test data, and an extensive optimizer benchmark suite with baselines at velo-code.github.io. △ Less

Submitted 17 November, 2022; originally announced November 2022.

Training Large-Vocabulary Neural Language Models by Private Federated Learning for Resource-Constrained Devices

Authors: Mingbin Xu, Congzheng Song, Ye Tian, Neha Agrawal, Filip Granqvist, Rogier van Dalen, Xiao Zhang, Arturo Argueta, Shiyi Han, Yaqiao Deng, Leo Liu, Anmol Walia, Alex Jin

Abstract: Federated Learning (FL) is a technique to train models using data distributed across devices. Differential Privacy (DP) provides a formal privacy guarantee for sensitive data. Our goal is to train a large neural network language model (NNLM) on compute-constrained devices while preserving privacy using FL and DP. However, the DP-noise introduced to the model increases as the model size grows, whic… ▽ More Federated Learning (FL) is a technique to train models using data distributed across devices. Differential Privacy (DP) provides a formal privacy guarantee for sensitive data. Our goal is to train a large neural network language model (NNLM) on compute-constrained devices while preserving privacy using FL and DP. However, the DP-noise introduced to the model increases as the model size grows, which often prevents convergence. We propose Partial Embedding Updates (PEU), a novel technique to decrease noise by decreasing payload size. Furthermore, we adopt Low Rank Adaptation (LoRA) and Noise Contrastive Estimation (NCE) to reduce the memory demands of large models on compute-constrained devices. This combination of techniques makes it possible to train large-vocabulary language models while preserving accuracy and privacy. △ Less

Submitted 18 July, 2022; originally announced July 2022.

A Learning-Based Approach to Approximate Coded Computation

Authors: Navneet Agrawal, Yuqin Qiu, Matthias Frey, Igor Bjelakovic, Setareh Maghsudi, Slawomir Stanczak, Jingge Zhu

Abstract: Lagrange coded computation (LCC) is essential to solving problems about matrix polynomials in a coded distributed fashion; nevertheless, it can only solve the problems that are representable as matrix polynomials. In this paper, we propose AICC, an AI-aided learning approach that is inspired by LCC but also uses deep neural networks (DNNs). It is appropriate for coded computation of more general f… ▽ More Lagrange coded computation (LCC) is essential to solving problems about matrix polynomials in a coded distributed fashion; nevertheless, it can only solve the problems that are representable as matrix polynomials. In this paper, we propose AICC, an AI-aided learning approach that is inspired by LCC but also uses deep neural networks (DNNs). It is appropriate for coded computation of more general functions. Numerical simulations demonstrate the suitability of the proposed approach for the coded computation of different matrix functions that are often utilized in digital signal processing. △ Less

Submitted 19 May, 2022; originally announced May 2022.

Comments: Submitted to IEEE Information Theory Workshop (ITW) 2022

Exploring Transformer Based Models to Identify Hate Speech and Offensive Content in English and Indo-Aryan Languages

Authors: Somnath Banerjee, Maulindu Sarkar, Nancy Agrawal, Punyajoy Saha, Mithun Das

Abstract: Hate speech is considered to be one of the major issues currently plaguing online social media. Repeated and repetitive exposure to hate speech has been shown to create physiological effects on the target users. Thus, hate speech, in all its forms, should be addressed on these platforms in order to maintain good health. In this paper, we explored several Transformer based machine learning models f… ▽ More Hate speech is considered to be one of the major issues currently plaguing online social media. Repeated and repetitive exposure to hate speech has been shown to create physiological effects on the target users. Thus, hate speech, in all its forms, should be addressed on these platforms in order to maintain good health. In this paper, we explored several Transformer based machine learning models for the detection of hate speech and offensive content in English and Indo-Aryan languages at FIRE 2021. We explore several models such as mBERT, XLMR-large, XLMR-base by team name "Super Mario". Our models came 2nd position in Code-Mixed Data set (Macro F1: 0.7107), 2nd position in Hindi two-class classification(Macro F1: 0.7797), 4th in English four-class category (Macro F1: 0.8006) and 12th in English two-class category (Macro F1: 0.6447). △ Less

Submitted 27 November, 2021; originally announced November 2021.

Comments: Accepted in FIRE'21 (Track HASOC - English and Indo-Aryan Languages)

MPC-Friendly Commitments for Publicly Verifiable Covert Security

Authors: Nitin Agrawal, James Bell, Adrià Gascón, Matt J. Kusner

Abstract: We address the problem of efficiently verifying a commitment in a two-party computation. This addresses the scenario where a party P1 commits to a value $x$ to be used in a subsequent secure computation with another party P2 that wants to receive assurance that P1 did not cheat, i.e. that $x$ was indeed the value inputted into the secure computation. Our constructions operate in the publicly verif… ▽ More We address the problem of efficiently verifying a commitment in a two-party computation. This addresses the scenario where a party P1 commits to a value $x$ to be used in a subsequent secure computation with another party P2 that wants to receive assurance that P1 did not cheat, i.e. that $x$ was indeed the value inputted into the secure computation. Our constructions operate in the publicly verifiable covert (PVC) security model, which is a relaxation of the malicious model of MPC appropriate in settings where P1 faces a reputational harm if caught cheating. We introduce the notion of PVC commitment scheme and indexed hash functions to build commitments schemes tailored to the PVC framework, and propose constructions for both arithmetic and Boolean circuits that result in very efficient circuits. From a practical standpoint, our constructions for Boolean circuits are $60\times$ faster to evaluate securely, and use $36\times$ less communication than baseline methods based on hashing. Moreover, we show that our constructions are tight in terms of required non-linear operations, by proving lower bounds on the nonlinear gate count of commitment verification circuits. Finally, we present a technique to amplify the security properties our constructions that allows to efficiently recover malicious guarantees with statistical security. △ Less

Submitted 27 January, 2022; v1 submitted 15 September, 2021; originally announced September 2021.

Comments: Appeared at ACM CCS 2021

Journal ref: ACM CCS 2021

Impact of data-splits on generalization: Identifying COVID-19 from cough and context

Authors: Makkunda Sharma, Nikhil Shenoy, Jigar Doshi, Piyush Bagad, Aman Dalmia, Parag Bhamare, Amrita Mahale, Saurabh Rane, Neeraj Agrawal, Rahul Panicker

Abstract: Rapidly scaling screening, testing and quarantine has shown to be an effective strategy to combat the COVID-19 pandemic. We consider the application of deep learning techniques to distinguish individuals with COVID from non-COVID by using data acquirable from a phone. Using cough and context (symptoms and meta-data) represent such a promising approach. Several independent works in this direction h… ▽ More Rapidly scaling screening, testing and quarantine has shown to be an effective strategy to combat the COVID-19 pandemic. We consider the application of deep learning techniques to distinguish individuals with COVID from non-COVID by using data acquirable from a phone. Using cough and context (symptoms and meta-data) represent such a promising approach. Several independent works in this direction have shown promising results. However, none of them report performance across clinically relevant data splits. Specifically, the performance where the development and test sets are split in time (retrospective validation) and across sites (broad validation). Although there is meaningful generalization across these splits the performance significantly varies (up to 0.1 AUC score). In addition, we study the performance of symptomatic and asymptomatic individuals across these three splits. Finally, we show that our model focuses on meaningful features of the input, cough bouts for cough and relevant symptoms for context. The code and checkpoints are available at https://github.com/WadhwaniAI/cough-against-covid △ Less

Submitted 5 June, 2021; originally announced June 2021.

Comments: Published as a workshop paper at ICLR 2021 AI for Public Health Workshop and ICLR 20201 Machine Learning for Preventing and Combating Pandemics Workshop

Exploring Design and Governance Challenges in the Development of Privacy-Preserving Computation

Authors: Nitin Agrawal, Reuben Binns, Max Van Kleek, Kim Laine, Nigel Shadbolt

Abstract: Homomorphic encryption, secure multi-party computation, and differential privacy are part of an emerging class of Privacy Enhancing Technologies which share a common promise: to preserve privacy whilst also obtaining the benefits of computational analysis. Due to their relative novelty, complexity, and opacity, these technologies provoke a variety of novel questions for design and governance. We i… ▽ More Homomorphic encryption, secure multi-party computation, and differential privacy are part of an emerging class of Privacy Enhancing Technologies which share a common promise: to preserve privacy whilst also obtaining the benefits of computational analysis. Due to their relative novelty, complexity, and opacity, these technologies provoke a variety of novel questions for design and governance. We interviewed researchers, developers, industry leaders, policymakers, and designers involved in their deployment to explore motivations, expectations, perceived opportunities and barriers to adoption. This provided insight into several pertinent challenges facing the adoption of these technologies, including: how they might make a nebulous concept like privacy computationally tractable; how to make them more usable by developers; and how they could be explained and made accountable to stakeholders and wider society. We conclude with implications for the development, deployment, and responsible governance of these privacy-preserving computation techniques. △ Less

Submitted 20 January, 2021; originally announced January 2021.

BlockSim-Net: A Network Based Blockchain Simulator

Authors: Nandini Agrawal, R Prashanthi, Osman Biçer, Alptekin Küpçü

Abstract: Since its proposal by Eyal and Sirer (CACM '13), selfish mining attack on proof-of-work blockchains has been studied extensively in terms of both improving its impact and defending against it. Before any defense is deployed in a real world blockchain system, it needs to be tested for security and dependability. However, real blockchain systems are too complex to conduct any test on or benchmark th… ▽ More Since its proposal by Eyal and Sirer (CACM '13), selfish mining attack on proof-of-work blockchains has been studied extensively in terms of both improving its impact and defending against it. Before any defense is deployed in a real world blockchain system, it needs to be tested for security and dependability. However, real blockchain systems are too complex to conduct any test on or benchmark the developed protocols. Some simulation environments have been proposed recently, such as BlockSim (Maher et al., '20). However, BlockSim is developed for the simulation of an entire network on a single CPU. Therefore, it is insufficient to capture the essence of a real blockchain network, as it is not distributed and the complications such as propagation delays that occur in reality cannot be simulated realistically enough. In this work, we propose BlockSim-Net, a simple, efficient, high performance, network-based blockchain simulator, to better reflect reality. △ Less

Submitted 27 November, 2020; v1 submitted 6 November, 2020; originally announced November 2020.

Universal Adversarial Perturbations: A Survey

Authors: Ashutosh Chaubey, Nikhil Agrawal, Kavya Barnwal, Keerat K. Guliani, Pramod Mehta

Abstract: Over the past decade, Deep Learning has emerged as a useful and efficient tool to solve a wide variety of complex learning problems ranging from image classification to human pose estimation, which is challenging to solve using statistical machine learning algorithms. However, despite their superior performance, deep neural networks are susceptible to adversarial perturbations, which can cause the… ▽ More Over the past decade, Deep Learning has emerged as a useful and efficient tool to solve a wide variety of complex learning problems ranging from image classification to human pose estimation, which is challenging to solve using statistical machine learning algorithms. However, despite their superior performance, deep neural networks are susceptible to adversarial perturbations, which can cause the network's prediction to change without making perceptible changes to the input image, thus creating severe security issues at the time of deployment of such systems. Recent works have shown the existence of Universal Adversarial Perturbations, which, when added to any image in a dataset, misclassifies it when passed through a target model. Such perturbations are more practical to deploy since there is minimal computation done during the actual attack. Several techniques have also been proposed to defend the neural networks against these perturbations. In this paper, we attempt to provide a detailed discussion on the various data-driven and data-independent methods for generating universal perturbations, along with measures to defend against such perturbations. We also cover the applications of such universal perturbations in various deep learning tasks. △ Less

Submitted 16 May, 2020; originally announced May 2020.

Comments: 20 pages, 17 figures

InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactions

Authors: Shikhar Vashishth, Soumya Sanyal, Vikram Nitin, Nilesh Agrawal, Partha Talukdar

Abstract: Most existing knowledge graphs suffer from incompleteness, which can be alleviated by inferring missing links based on known facts. One popular way to accomplish this is to generate low-dimensional embeddings of entities and relations, and use these to make inferences. ConvE, a recently proposed approach, applies convolutional filters on 2D reshapings of entity and relation embeddings in order to… ▽ More Most existing knowledge graphs suffer from incompleteness, which can be alleviated by inferring missing links based on known facts. One popular way to accomplish this is to generate low-dimensional embeddings of entities and relations, and use these to make inferences. ConvE, a recently proposed approach, applies convolutional filters on 2D reshapings of entity and relation embeddings in order to capture rich interactions between their components. However, the number of interactions that ConvE can capture is limited. In this paper, we analyze how increasing the number of these interactions affects link prediction performance, and utilize our observations to propose InteractE. InteractE is based on three key ideas -- feature permutation, a novel feature reshaping, and circular convolution. Through extensive experiments, we find that InteractE outperforms state-of-the-art convolutional link prediction baselines on FB15k-237. Further, InteractE achieves an MRR score that is 9%, 7.5%, and 23% better than ConvE on the FB15k-237, WN18RR and YAGO3-10 datasets respectively. The results validate our central hypothesis -- that increasing feature interaction is beneficial to link prediction performance. We make the source code of InteractE available to encourage reproducible research. △ Less

Submitted 24 September, 2020; v1 submitted 1 November, 2019; originally announced November 2019.

Comments: Accepted at AAAI 2020

QUOTIENT: Two-Party Secure Neural Network Training and Prediction

Authors: Nitin Agrawal, Ali Shahin Shamsabadi, Matt J. Kusner, Adrià Gascón

Abstract: Recently, there has been a wealth of effort devoted to the design of secure protocols for machine learning tasks. Much of this is aimed at enabling secure prediction from highly-accurate Deep Neural Networks (DNNs). However, as DNNs are trained on data, a key question is how such models can be also trained securely. The few prior works on secure DNN training have focused either on designing custom… ▽ More Recently, there has been a wealth of effort devoted to the design of secure protocols for machine learning tasks. Much of this is aimed at enabling secure prediction from highly-accurate Deep Neural Networks (DNNs). However, as DNNs are trained on data, a key question is how such models can be also trained securely. The few prior works on secure DNN training have focused either on designing custom protocols for existing training algorithms, or on developing tailored training algorithms and then applying generic secure protocols. In this work, we investigate the advantages of designing training algorithms alongside a novel secure protocol, incorporating optimizations on both fronts. We present QUOTIENT, a new method for discretized training of DNNs, along with a customized secure two-party protocol for it. QUOTIENT incorporates key components of state-of-the-art DNN training such as layer normalization and adaptive gradient methods, and improves upon the state-of-the-art in DNN training in two-party computation. Compared to prior work, we obtain an improvement of 50X in WAN time and 6% in absolute accuracy. △ Less

Submitted 7 July, 2019; originally announced July 2019.

A Scalable Max-Consensus Protocol For Noisy Ultra-Dense Networks

Authors: Navneet Agrawal, Matthias Frey, Slawomir Stanczak

Abstract: We introduce \emph{ScalableMax}, a novel communication scheme for achieving max-consensus in a network of multiple agents which harnesses the interference in the wireless channel as well as its multicast capabilities. In a sufficiently dense network, the amount of communication resources required grows logarithmically with the number of nodes, while in state-of-the-art approaches, this growth is a… ▽ More We introduce \emph{ScalableMax}, a novel communication scheme for achieving max-consensus in a network of multiple agents which harnesses the interference in the wireless channel as well as its multicast capabilities. In a sufficiently dense network, the amount of communication resources required grows logarithmically with the number of nodes, while in state-of-the-art approaches, this growth is at least linear. ScalableMax can handle additive noise and works well in a high SNR regime. For medium and low SNR, we propose the \emph{ScalableMax-EC} scheme, which extends the ideas of ScalableMax by introducing a novel error correction scheme. It achieves lower error rates at the cost of using more channel resources. However, it preserves the logarithmic growth with the number of agents in the system. △ Less

Submitted 14 May, 2019; v1 submitted 7 March, 2019; originally announced March 2019.

Comments: v2: Revised version after reviews; slightly extended w.r.t. version submitted to SPAWC

Journal ref: 2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), Cannes, France, 2019, pp. 1-5

KLUCB Approach to Copeland Bandits

Authors: Nischal Agrawal, Prasanna Chaporkar

Abstract: Multi-armed bandit(MAB) problem is a reinforcement learning framework where an agent tries to maximise her profit by proper selection of actions through absolute feedback for each action. The dueling bandits problem is a variation of MAB problem in which an agent chooses a pair of actions and receives relative feedback for the chosen action pair. The dueling bandits problem is well suited for mode… ▽ More Multi-armed bandit(MAB) problem is a reinforcement learning framework where an agent tries to maximise her profit by proper selection of actions through absolute feedback for each action. The dueling bandits problem is a variation of MAB problem in which an agent chooses a pair of actions and receives relative feedback for the chosen action pair. The dueling bandits problem is well suited for modelling a setting in which it is not possible to provide quantitative feedback for each action, but qualitative feedback for each action is preferred as in the case of human feedback. The dueling bandits have been successfully applied in applications such as online rank elicitation, information retrieval, search engine improvement and clinical online recommendation. We propose a new method called Sup-KLUCB for K-armed dueling bandit problem specifically Copeland bandit problem by converting it into a standard MAB problem. Instead of using MAB algorithm independently for each action in a pair as in Sparring and in Self-Sparring algorithms, we combine a pair of action and use it as one action. Previous UCB algorithms such as Relative Upper Confidence Bound(RUCB) can be applied only in case of Condorcet dueling bandits, whereas this algorithm applies to general Copeland dueling bandits, including Condorcet dueling bandits as a special case. Our empirical results outperform state of the art Double Thompson Sampling(DTS) in case of Copeland dueling bandits. △ Less

Submitted 7 February, 2019; originally announced February 2019.

Comments: 10 pages, 2 figures

Unsupervised Learning from Narrated Instruction Videos

Authors: Jean-Baptiste Alayrac, Piotr Bojanowski, Nishant Agrawal, Josef Sivic, Ivan Laptev, Simon Lacoste-Julien

Abstract: We address the problem of automatically learning the main steps to complete a certain task, such as changing a car tire, from a set of narrated instruction videos. The contributions of this paper are three-fold. First, we develop a new unsupervised learning approach that takes advantage of the complementary nature of the input video and the associated narration. The method solves two clustering pr… ▽ More We address the problem of automatically learning the main steps to complete a certain task, such as changing a car tire, from a set of narrated instruction videos. The contributions of this paper are three-fold. First, we develop a new unsupervised learning approach that takes advantage of the complementary nature of the input video and the associated narration. The method solves two clustering problems, one in text and one in video, applied one after each other and linked by joint constraints to obtain a single coherent sequence of steps in both modalities. Second, we collect and annotate a new challenging dataset of real-world instruction videos from the Internet. The dataset contains about 800,000 frames for five different tasks that include complex interactions between people and objects, and are captured in a variety of indoor and outdoor settings. Third, we experimentally demonstrate that the proposed method can automatically discover, in an unsupervised manner, the main steps to achieve the task and locate the steps in the input videos. △ Less

Submitted 28 June, 2016; v1 submitted 30 June, 2015; originally announced June 2015.

Comments: Appears in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016). 21 pages

ACM Class: I.5.1; I.5.4; I.2

Comparison Clustering using Cosine and Fuzzy set based Similarity Measures of Text Documents

Authors: Manan Mohan Goyal, Neha Agrawal, Manoj Kumar Sarma, Nayan Jyoti Kalita

Abstract: Keeping in consideration the high demand for clustering, this paper focuses on understanding and implementing K-means clustering using two different similarity measures. We have tried to cluster the documents using two different measures rather than clustering it with Euclidean distance. Also a comparison is drawn based on accuracy of clustering between fuzzy and cosine similarity measure. The sta… ▽ More Keeping in consideration the high demand for clustering, this paper focuses on understanding and implementing K-means clustering using two different similarity measures. We have tried to cluster the documents using two different measures rather than clustering it with Euclidean distance. Also a comparison is drawn based on accuracy of clustering between fuzzy and cosine similarity measure. The start time and end time parameters for formation of clusters are used in deciding optimum similarity measure. △ Less

Submitted 1 May, 2015; originally announced May 2015.

Comments: 4 pages, International Conference on Computing and Communication Systems 2015 (I3CS'15), ISBM: 978-1-4799-5857-01, 2015

Towards Refactoring of DMARF and GIPSY Case Studies -- a Team 8 SOEN6471-S14 Project Report

Authors: Nitish Agrawal, Rachit Naidu, Sadhana Viswanathan, Vikram Wankhede, Zakaria Nasereldine, Zohaib S. Kiyani

Abstract: Of the factors that determines the quality of a software system is its design and architecture. Having a good and clear design and architecture allows the system to evolve (plan and add new features), be easier to comprehend, easier to develop, easier to maintain; and in conclusion increase the life time of the, and being more competitive in its market. In the following paper we study the architec… ▽ More Of the factors that determines the quality of a software system is its design and architecture. Having a good and clear design and architecture allows the system to evolve (plan and add new features), be easier to comprehend, easier to develop, easier to maintain; and in conclusion increase the life time of the, and being more competitive in its market. In the following paper we study the architecture of two different systems: GIPSY and DMARF. This paper provides a general overview of these two systems. What are these two systems, purpose, architecture, and their design patterns? Classes with week architecture and design, and code smells were also identified and some refactorings were suggested and implemented. Several tools were used throughout the paper for several purpose. LOGICSCOPE, JDeodoant, McCabe were used to identify classes with weak designs and code smells. Other tools and plugins were also used to identify class designs and relationships between classes such as ObjectAid (Eclipse plugin). △ Less

Submitted 23 December, 2014; originally announced December 2014.

Comments: 53 pages

ACM Class: D.2; K.6; H.5.2

An efficient distributed learning algorithm based on effective local functional approximations

Authors: Dhruv Mahajan, Nikunj Agrawal, S. Sathiya Keerthi, S. Sundararajan, Leon Bottou

Abstract: Scalable machine learning over big data is an important problem that is receiving a lot of attention in recent years. On popular distributed environments such as Hadoop running on a cluster of commodity machines, communication costs are substantial and algorithms need to be designed suitably considering those costs. In this paper we give a novel approach to the distributed training of linear class… ▽ More Scalable machine learning over big data is an important problem that is receiving a lot of attention in recent years. On popular distributed environments such as Hadoop running on a cluster of commodity machines, communication costs are substantial and algorithms need to be designed suitably considering those costs. In this paper we give a novel approach to the distributed training of linear classifiers (involving smooth losses and L2 regularization) that is designed to reduce the total communication costs. At each iteration, the nodes minimize locally formed approximate objective functions; then the resulting minimizers are combined to form a descent direction to move. Our approach gives a lot of freedom in the formation of the approximate objective function as well as in the choice of methods to solve them. The method is shown to have $O(log(1/ε))$ time convergence. The method can be viewed as an iterative parameter mixing method. A special instantiation yields a parallel stochastic gradient descent method with strong convergence. When communication times between nodes are large, our method is much faster than the Terascale method (Agarwal et al., 2011), which is a state of the art distributed solver based on the statistical query model (Chuet al., 2006) that computes function and gradient values in a distributed fashion. We also evaluate against other recent distributed methods and demonstrate superior performance of our method. △ Less

Submitted 16 March, 2015; v1 submitted 31 October, 2013; originally announced October 2013.

Reconstruction and Repair Degree of Fractional Repetition Codes

Authors: Krishna Gopal Benerjee, Manish K. Gupta, Nikhil Agrawal

Abstract: Given a Fractional Repetition code, finding the reconstruction and repair degree in a distributed storage system is an important problem. In this work, we present algorithms for computing the reconstruction and repair degree of fractional repetition codes. Given a Fractional Repetition code, finding the reconstruction and repair degree in a distributed storage system is an important problem. In this work, we present algorithms for computing the reconstruction and repair degree of fractional repetition codes. △ Less

Submitted 20 May, 2013; originally announced May 2013.

Comments: A one page abstract of this paper appears as a poster in IEEE Netcod 2013

Green Cellular Network Deployment To Reduce RF Pollution

Authors: Sumit Katiyar, R. K. Jain, N. K. Agrawal

Abstract: As the mobile telecommunication systems are growing tremendously all over the world, the numbers of handheld and base stations are also rapidly growing and it became very popular to see these base stations distributed everywhere in the neighborhood and on roof tops which has caused a considerable amount of panic to the public in Palestine concerning wither the radiated electromagnetic fields from… ▽ More As the mobile telecommunication systems are growing tremendously all over the world, the numbers of handheld and base stations are also rapidly growing and it became very popular to see these base stations distributed everywhere in the neighborhood and on roof tops which has caused a considerable amount of panic to the public in Palestine concerning wither the radiated electromagnetic fields from these base stations may cause any health effect or hazard. Recently UP High Court in India ordered for removal of BTS towers from residential area, it has created panic among cellular communication network designers too. Green cellular networks could be a solution for the above problem. This paper deals with green cellular networks with the help of multi-layer overlaid hierarchical structure (macro / micro / pico / femto cells). Macrocell for area coverage, micro for pedestrian and a slow moving traffic while pico for indoor use and femto for individual high capacity users. This could be the answer of the problem of energy conservation and enhancement of spectral density also. △ Less

Submitted 16 April, 2012; originally announced April 2012.

Comments: 6 pages, 6 figures. arXiv admin note: substantial text overlap with arXiv:1204.2101, arXiv:1110.2627, and with arXiv:0803.0952 and arXiv:0803.0952 by other authors

R.F. Pollution Reduction in Cellular Communication

Authors: Sumit Katiyar, R. K. Jain, N. K. Agrawal

Abstract: R. F. pollution has been recognized as health hazard in India in the prevailing circumstances. There is lot of hue and cry against cellular towers installed in residential area. Recently high court in India has issued an order not to install towers in residential areas. For meeting the exponential demand of cellular communication in India this will be a set back for future growth. An appropriate s… ▽ More R. F. pollution has been recognized as health hazard in India in the prevailing circumstances. There is lot of hue and cry against cellular towers installed in residential area. Recently high court in India has issued an order not to install towers in residential areas. For meeting the exponential demand of cellular communication in India this will be a set back for future growth. An appropriate solution has to be developed for meeting demand as well as RF pollution concern of the society. This paper deals with the installation of low power base stations in residential areas instead of high power macro cell base stations. Macro stations are proposed to be used for fast traffic, low power micro cell for a slow traffic / pedestrian and pico cell / femto cell for indoor use. These cells will be in hierarchical structure along with adaptive frequency allocation techniques and A-SDMA approach. △ Less

Submitted 10 April, 2012; originally announced April 2012.

Comments: 6 pages, 7 figures, international journal, International Journal of Scientific & Engineering Research, Volume 3, Issue 3, March -2012

An Intelligent Approach for Dense Urban Area in existing 2G / 2.5G

Authors: Sumit Katiyar, Prof. R. K. Jain, Prof. N. K. Agrawal

Abstract: In the prevailing scenario audio, video, data services (i.e. internet), multimedia and broadcasting etc. are being integrated. Decreasing cell size increases capacity but at the same time increases fluctuation and interference too. The intelligence approach is the only answer in developing countries where frequency and power are scarce resources. In this paper, we have tried to integrate all prove… ▽ More In the prevailing scenario audio, video, data services (i.e. internet), multimedia and broadcasting etc. are being integrated. Decreasing cell size increases capacity but at the same time increases fluctuation and interference too. The intelligence approach is the only answer in developing countries where frequency and power are scarce resources. In this paper, we have tried to integrate all proven technologies in networking such as in-building network, micro zone, intelligent micro cell, deployment along city streets, tunnels, subway coverage etc. along with adaptive frequency allocation in hierarchical approach with the help of adaptive / intelligent antenna system. A-SDMA approach will further enhance spectral efficiency as well as QoS (Quality of Service). It can be proved beyond doubt that this integrated approach will convert 2G / 2.5G systems capable of handling the prevailing demand at reduced cost. In addition to it, integrated approach will save power and reduce RF pollution. In this paper we have explained the ill effect of cellular growth in terms of health hazard and increased power consumption. We have also suggested ways and means to overcome these problems (spectral density / capacity, QoS, power consumption and RF pollution etc.). △ Less

Submitted 10 April, 2012; originally announced April 2012.

Comments: 6 pages, 7 figures. arXiv admin note: substantial text overlap with arXiv:1110.2627

Journal ref: International Journal of Scientific & Engineering Research - Volume 2, Issue 12, December -2011

Smart Antenna for Cellular Mobile Communication

Authors: R. K. Jain, Sumit Katiyar, N. K. Agrawal

Abstract: The adoption of smart / adaptive antenna techniques in future wireless systems is expected to have a significant impact on the efficient use of the spectrum, the minimization of the cost of establishing new wireless networks, the optimization of service quality and realization of transparent operation across multi technology wireless networks [1]. This paper presents brief account on smart antenna… ▽ More The adoption of smart / adaptive antenna techniques in future wireless systems is expected to have a significant impact on the efficient use of the spectrum, the minimization of the cost of establishing new wireless networks, the optimization of service quality and realization of transparent operation across multi technology wireless networks [1]. This paper presents brief account on smart antenna (SA) system. SAs can place nulls in the direction of interferers via adaptive updating of weights linked to each antenna element. SAs thus cancel out most of the co-channel interference resulting in better quality of reception and lower dropped calls. SAs can also track the user within a cell via direction of arrival algorithms [2]. This paper explains the architecture, evolution and how the smart / adaptive antenna differs from the basic format of antenna. The paper further explains about the radiation pattern of the antenna and why it is highly preferred in its relative field. The capabilities of smart / adaptive antenna are easily employable to Cognitive Radio and OFDMA system. △ Less

Submitted 9 April, 2012; originally announced April 2012.

Comments: 12 pages, 8 figures, international journal

Journal ref: VSRD International Journal of Electrical, Electronics & Comm. Engg. Vol. 1 (9), 2011

R.F. Pollution Reduction in Cellular Communication

Authors: Sumit Katiyar, R. K. Jain, N. K. Agrawal

Abstract: Erroneous submission in violation of copyright removed by arXiv admin. Erroneous submission in violation of copyright removed by arXiv admin. △ Less

Submitted 9 April, 2012; originally announced April 2012.

Comments: Erroneous submission in violation of copyright

Hierarchical Cellular Structures in High-Capacity Cellular Communication Systems

Authors: R. K. Jain, Sumit Katiyar, N. K. Agrawal

Abstract: In the prevailing cellular environment, it is important to provide the resources for the fluctuating traffic demand exactly in the place and at the time where and when they are needed. In this paper, we explored the ability of hierarchical cellular structures with inter layer reuse to increase the capacity of mobile communication network by applying total frequency hopping (T-FH) and adaptive freq… ▽ More In the prevailing cellular environment, it is important to provide the resources for the fluctuating traffic demand exactly in the place and at the time where and when they are needed. In this paper, we explored the ability of hierarchical cellular structures with inter layer reuse to increase the capacity of mobile communication network by applying total frequency hopping (T-FH) and adaptive frequency allocation (AFA) as a strategy to reuse the macro and micro cell resources without frequency planning in indoor pico cells [11]. The practical aspects for designing macro- micro cellular overlays in the existing big urban areas are also explained [4]. Femto cells are inducted in macro / micro / pico cells hierarchical structure to achieve the required QoS cost effectively. △ Less

Submitted 12 October, 2011; originally announced October 2011.

Comments: 7 pages, 8 figures, International Journal

Journal ref: (IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 2, No 9, 2011, 51-57

Survey of Latest Wireless Cellular Technologies for Enhancement of Spectral Density at Reduced Cost

Authors: R. K. Jain, Sumit Katiyar, N. K. Agrawal

Abstract: The future of mobile wireless communication networks will include existing 3rd generation, 4th generation (implemented in Japan, USA, South Korea etc.), 5th generation (based on cognitive radio which implies the whole wireless world interconnection & WISDOM - Wireless innovative System for Dynamic Operating Megacommunications concept), 6th generation (with very high data rates Quality of Service (… ▽ More The future of mobile wireless communication networks will include existing 3rd generation, 4th generation (implemented in Japan, USA, South Korea etc.), 5th generation (based on cognitive radio which implies the whole wireless world interconnection & WISDOM - Wireless innovative System for Dynamic Operating Megacommunications concept), 6th generation (with very high data rates Quality of Service (QoS) and service applications) and 7th generation (with space roaming). This paper is focused on the specifications of future generations and latest technologies to be used in future wireless mobile communication networks. However keeping in view the general poor masses of India, some of the future generation technologies will be embedded with 2G and 2.5G so that general masses may get the advantage of internet, multimedia services and the operators may get proper revenues with little extra expenditure in the existing mobile communication networks. △ Less

Submitted 12 October, 2011; originally announced October 2011.

Comments: 7 pages, 4 figures, international journal

Journal ref: IJCSI International Journal of Computer Science Issues, Vol. 8, Issue 3, No. 2, 2011, 491-497