Skip to main content

Showing 1–26 of 26 results for author: Fonseca, J

Searching in archive cs. Search in all archives.
.
  1. arXiv:2601.23068  [pdf, ps, other

    cs.LG cs.AI

    ExplainerPFN: Towards tabular foundation models for model-free zero-shot feature importance estimations

    Authors: Joao Fonseca, Julia Stoyanovich

    Abstract: Computing the importance of features in supervised classification tasks is critical for model interpretability. Shapley values are a widely used approach for explaining model predictions, but require direct access to the underlying model, an assumption frequently violated in real-world deployments. Further, even when model access is possible, their exact computation may be prohibitively expensive.… ▽ More

    Submitted 30 January, 2026; originally announced January 2026.

    Comments: 18 pages, 7 figures

  2. arXiv:2505.08345  [pdf, ps, other

    cs.LG cs.AI

    SHAP-based Explanations are Sensitive to Feature Representation

    Authors: Hyunseung Hwang, Andrew Bell, Joao Fonseca, Venetia Pliatsika, Julia Stoyanovich, Steven Euijong Whang

    Abstract: Local feature-based explanations are a key component of the XAI toolkit. These explanations compute feature importance values relative to an ``interpretable'' feature representation. In tabular data, feature values themselves are often considered interpretable. This paper examines the impact of data engineering choices on local feature-based explanations. We demonstrate that simple, common data en… ▽ More

    Submitted 13 May, 2025; originally announced May 2025.

    Comments: Accepted to ACM FAccT 2025

  3. arXiv:2501.02018  [pdf, other

    cs.CL cs.AI cs.CR cs.LG

    Safeguarding Large Language Models in Real-time with Tunable Safety-Performance Trade-offs

    Authors: Joao Fonseca, Andrew Bell, Julia Stoyanovich

    Abstract: Large Language Models (LLMs) have been shown to be susceptible to jailbreak attacks, or adversarial attacks used to illicit high risk behavior from a model. Jailbreaks have been exploited by cybercriminals and blackhat actors to cause significant harm, highlighting the critical need to safeguard widely-deployed models. Safeguarding approaches, which include fine-tuning models or having LLMs "self-… ▽ More

    Submitted 2 January, 2025; originally announced January 2025.

  4. arXiv:2410.05305   

    cs.CL cs.AI

    Output Scouting: Auditing Large Language Models for Catastrophic Responses

    Authors: Andrew Bell, Joao Fonseca

    Abstract: Recent high profile incidents in which the use of Large Language Models (LLMs) resulted in significant harm to individuals have brought about a growing interest in AI safety. One reason LLM safety issues occur is that models often have at least some non-zero probability of producing harmful outputs. In this work, we explore the following scenario: imagine an AI safety auditor is searching for cata… ▽ More

    Submitted 28 March, 2025; v1 submitted 4 October, 2024; originally announced October 2024.

    Comments: Work not ready, further experiments needed to validate the method

  5. arXiv:2407.05467  [pdf, other

    cs.DC cs.AI

    The infrastructure powering IBM's Gen AI model development

    Authors: Talia Gershon, Seetharami Seelam, Brian Belgodere, Milton Bonilla, Lan Hoang, Danny Barnett, I-Hsin Chung, Apoorve Mohan, Ming-Hung Chen, Lixiang Luo, Robert Walkup, Constantinos Evangelinos, Shweta Salaria, Marc Dombrowa, Yoonho Park, Apo Kayi, Liran Schour, Alim Alim, Ali Sydney, Pavlos Maniotis, Laurent Schares, Bernard Metzler, Bengi Karacali-Akyamac, Sophia Wen, Tatsuhiro Chiba , et al. (122 additional authors not shown)

    Abstract: AI Infrastructure plays a key role in the speed and cost-competitiveness of developing and deploying advanced AI models. The current demand for powerful AI infrastructure for model training is driven by the emergence of generative AI and foundational models, where on occasion thousands of GPUs must cooperate on a single training job for the model to be trained in a reasonable time. Delivering effi… ▽ More

    Submitted 13 January, 2025; v1 submitted 7 July, 2024; originally announced July 2024.

    Comments: Corresponding Authors: Talia Gershon, Seetharami Seelam,Brian Belgodere, Milton Bonilla

  6. arXiv:2407.02737  [pdf, other

    q-bio.QM cs.LG

    Development of Machine Learning Classifiers for Blood-based Diagnosis and Prognosis of Suspected Acute Infections and Sepsis

    Authors: Ljubomir Buturovic, Michael Mayhew, Roland Luethy, Kirindi Choi, Uros Midic, Nandita Damaraju, Yehudit Hasin-Brumshtein, Amitesh Pratap, Rhys M. Adams, Joao Fonseca, Ambika Srinath, Paul Fleming, Claudia Pereira, Oliver Liesenfeld, Purvesh Khatri, Timothy Sweeney

    Abstract: We applied machine learning to the unmet medical need of rapid and accurate diagnosis and prognosis of acute infections and sepsis in emergency departments. Our solution consists of a Myrna (TM) Instrument and embedded TriVerity (TM) classifiers. The instrument measures abundances of 29 messenger RNAs in patient's blood, subsequently used as features for machine learning. The classifiers convert t… ▽ More

    Submitted 2 July, 2024; originally announced July 2024.

    Comments: 16 pages, 6 figures

    Journal ref: Proceedings of Machine Learning Research, Vol. 259: Proceedings of the 4th Machine Learning for Health Symposium (ML4H), 2025, pp. 154-170

  7. ShaRP: Explaining Rankings and Preferences with Shapley Values

    Authors: Venetia Pliatsika, Joao Fonseca, Kateryna Akhynko, Ivan Shevchenko, Julia Stoyanovich

    Abstract: Algorithmic decisions in critical domains such as hiring, college admissions, and lending are often based on rankings. Given the impact of these decisions on individuals, organizations, and population groups, it is essential to understand them - to help individuals improve their ranking position, design better ranking procedures, and ensure legal compliance. In this paper, we argue that explainabi… ▽ More

    Submitted 28 July, 2025; v1 submitted 29 January, 2024; originally announced January 2024.

    Comments: Accepted in VLDB

    Journal ref: VLDB, Volume 18, Issue 11, Year 2025

  8. arXiv:2401.16088  [pdf, other

    cs.LG cs.CY

    Fairness in Algorithmic Recourse Through the Lens of Substantive Equality of Opportunity

    Authors: Andrew Bell, Joao Fonseca, Carlo Abrate, Francesco Bonchi, Julia Stoyanovich

    Abstract: Algorithmic recourse -- providing recommendations to those affected negatively by the outcome of an algorithmic system on how they can take action and change that outcome -- has gained attention as a means of giving persons agency in their interactions with artificial intelligence (AI) systems. Recent work has shown that even if an AI decision-making classifier is ``fair'' (according to some reaso… ▽ More

    Submitted 29 January, 2024; originally announced January 2024.

  9. arXiv:2312.16363  [pdf, other

    cs.CG

    Polygon Detection from a Set of Lines

    Authors: Alfredo Ferreira Jr., Manuel J. Fonseca, Joaquim A. Jorge

    Abstract: Detecting polygons defined by a set of line segments in a plane is an important step in analyzing vector drawings. This paper presents an approach combining several algorithms to detect basic polygons from arbitrary line segments. The resulting algorithm runs in polynomial time and space, with complexities of $O\bigl((N + M)^4\bigr)$ and $O\bigl((N + M)^2\bigr)$, where $N$ is the number of line se… ▽ More

    Submitted 26 December, 2023; originally announced December 2023.

    Comments: 5 pages, 5 figures, 1 table

  10. arXiv:2309.06969  [pdf, other

    cs.LG cs.AI cs.CY

    Setting the Right Expectations: Algorithmic Recourse Over Time

    Authors: Joao Fonseca, Andrew Bell, Carlo Abrate, Francesco Bonchi, Julia Stoyanovich

    Abstract: Algorithmic systems are often called upon to assist in high-stakes decision making. In light of this, algorithmic recourse, the principle wherein individuals should be able to take action against an undesirable outcome made by an algorithmic system, is receiving growing attention. The bulk of the literature on algorithmic recourse to-date focuses primarily on how to provide recourse to a single in… ▽ More

    Submitted 13 September, 2023; originally announced September 2023.

  11. arXiv:2306.10807  [pdf, other

    cs.DL physics.soc-ph

    The Myth of Meritocracy and the Matilda Effect in STEM: Paper Acceptance and Paper Citation

    Authors: Joana Fonseca

    Abstract: Biases against women in the workplace have been documented in various studies. There is also a growing body of literature on biases within academia. But particularly in STEM, due to the heavily male-dominated field, studies suggest that if one's gender is identifiable, women are more likely to get their papers rejected and not cited as often as men. We propose two simple modifications to tackle ge… ▽ More

    Submitted 19 June, 2023; originally announced June 2023.

  12. arXiv:2305.19421  [pdf, other

    cs.RO cs.AI cs.LG

    Data and Knowledge for Overtaking Scenarios in Autonomous Driving

    Authors: Mariana Pinto, Inês Dutra, Joaquim Fonseca

    Abstract: Autonomous driving has become one of the most popular research topics within Artificial Intelligence. An autonomous vehicle is understood as a system that combines perception, decision-making, planning, and control. All of those tasks require that the vehicle collects surrounding data in order to make a good decision and action. In particular, the overtaking maneuver is one of the most critical ac… ▽ More

    Submitted 30 May, 2023; originally announced May 2023.

    Comments: 24 pages

  13. arXiv:2302.06294  [pdf, other

    eess.IV cs.CV cs.LG

    CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection

    Authors: Chinedu Innocent Nwoye, Tong Yu, Saurav Sharma, Aditya Murali, Deepak Alapatt, Armine Vardazaryan, Kun Yuan, Jonas Hajek, Wolfgang Reiter, Amine Yamlahi, Finn-Henri Smidt, Xiaoyang Zou, Guoyan Zheng, Bruno Oliveira, Helena R. Torres, Satoshi Kondo, Satoshi Kasai, Felix Holm, Ege Özsoy, Shuangchun Gui, Han Li, Sista Raviteja, Rachana Sathish, Pranav Poudel, Binod Bhattarai , et al. (24 additional authors not shown)

    Abstract: Formalizing surgical activities as triplets of the used instruments, actions performed, and target anatomies is becoming a gold standard approach for surgical activity modeling. The benefit is that this formalization helps to obtain a more detailed understanding of tool-tissue interaction which can be used to develop better Artificial Intelligence assistance for image-guided surgery. Earlier effor… ▽ More

    Submitted 14 July, 2023; v1 submitted 13 February, 2023; originally announced February 2023.

    Comments: MICCAI EndoVis CholecTriplet2022 challenge report. Published at Elsevier journal of Medical Image Analysis. 25 pages, 15 figures, 8 tables

    Journal ref: Medical Image Analysis, Volume 89, 2023, 102888, ISSN 1361-8415

  14. arXiv:2207.08817  [pdf, other

    cs.LG

    Research Trends and Applications of Data Augmentation Algorithms

    Authors: Joao Fonseca, Fernando Bacao

    Abstract: In the Machine Learning research community, there is a consensus regarding the relationship between model complexity and the required amount of data and computation power. In real world applications, these computational requirements are not always available, motivating research on regularization methods. In addition, current and past research have shown that simpler classification algorithms can r… ▽ More

    Submitted 2 August, 2022; v1 submitted 18 July, 2022; originally announced July 2022.

    Comments: 23 pages, 9 figures, 5 tables

  15. CholecTriplet2021: A benchmark challenge for surgical action triplet recognition

    Authors: Chinedu Innocent Nwoye, Deepak Alapatt, Tong Yu, Armine Vardazaryan, Fangfang Xia, Zixuan Zhao, Tong Xia, Fucang Jia, Yuxuan Yang, Hao Wang, Derong Yu, Guoyan Zheng, Xiaotian Duan, Neil Getty, Ricardo Sanchez-Matilla, Maria Robu, Li Zhang, Huabin Chen, Jiacheng Wang, Liansheng Wang, Bokai Zhang, Beerend Gerats, Sista Raviteja, Rachana Sathish, Rong Tao , et al. (37 additional authors not shown)

    Abstract: Context-aware decision support in the operating room can foster surgical safety and efficiency by leveraging real-time feedback from surgical workflow analysis. Most existing works recognize surgical activities at a coarse-grained level, such as phases, steps or events, leaving out fine-grained interaction details about the surgical activity; yet those are needed for more helpful AI assistance in… ▽ More

    Submitted 29 December, 2022; v1 submitted 10 April, 2022; originally announced April 2022.

    Comments: CholecTriplet2021 challenge report. Paper accepted at Elsevier journal of Medical Image Analysis. 22 pages, 8 figures, 11 tables. Challenge website: https://cholectriplet2021.grand-challenge.org

    Journal ref: Medical Image Analysis 86 (2023) 102803

  16. arXiv:2201.02418  [pdf, other

    cs.HC

    Developing Assistive Technology to Support Reminiscence Therapy: A User-Centered Study to Identify Caregivers' Needs

    Authors: Soraia M. Alarcão, André Santana, Carolina Maruta, Manuel J. Fonseca

    Abstract: Reminiscence therapy is an inexpensive non-pharmacological therapy commonly used due to its therapeutic value for PwD, as it can be used to promote independence, positive moods and behavior, and improve their quality of life. Caregivers are one of the main pillars in the adoption of digital technologies for reminiscence therapy, as they are responsible for its administration. Despite their compreh… ▽ More

    Submitted 7 January, 2022; originally announced January 2022.

    Comments: 27 pages, 2 figures, Manuscript submitted to the the Special Issue on Advances in Human-Centred Dementia Technology of the International Journal of Human-Computer Studies

  17. arXiv:2009.05560  [pdf, other

    cs.CY cs.CL cs.SI

    Narratives and Needs: Analyzing Experiences of Cyclone Amphan Using Twitter Discourse

    Authors: Ancil Crayton, João Fonseca, Kanav Mehra, Michelle Ng, Jared Ross, Marcelo Sandoval-Castañeda, Rachel von Gnechten

    Abstract: People often turn to social media to comment upon and share information about major global events. Accordingly, social media is receiving increasing attention as a rich data source for understanding people's social, political and economic experiences of extreme weather events. In this paper, we contribute two novel methodologies that leverage Twitter discourse to characterize narratives and identi… ▽ More

    Submitted 11 September, 2020; originally announced September 2020.

    Comments: 6 pages, 4 figures, 1 table

  18. arXiv:1903.05993  [pdf, other

    cs.RO

    Cooperative decentralized circumnavigation with application to algal bloom tracking

    Authors: Joana Fonseca, Jieqiang Wei, Karl H. Johansson, Tor Arne Johansen

    Abstract: Harmful algal blooms occur frequently and deteriorate water quality. A reliable method is proposed in this paper to track algal blooms using a set of autonomous surface robots. A satellite image indicates the existence and initial location of the algal bloom for the deployment of the robot system. The algal bloom area is approximated by a circle with time varying location and size. This circle is… ▽ More

    Submitted 14 March, 2019; originally announced March 2019.

  19. arXiv:1809.07829  [pdf, other

    cs.HC

    Personal Virtual Traffic Light Systems

    Authors: Vanessa Martins, João Rufino, Bruno Fernandes, Luís Silva, João Almeida, Joaquim Ferreira, José Fonseca

    Abstract: Traffic control management at intersections, a challenging and complex field of study, aims to attain a balance between safety and efficient traffic control. Nowadays, traffic control at intersections is typically done by traffic light systems which are not optimal and exhibit several drawbacks, e.g. poor efficiency and real-time adaptability. With the advent of Intelligent Transportation Systems… ▽ More

    Submitted 20 September, 2018; originally announced September 2018.

    Comments: 7 pages, 12 figures

  20. arXiv:1702.06898  [pdf, other

    cs.MS cs.DC physics.flu-dyn

    Enhancing speed and scalability of the ParFlow simulation code

    Authors: Carsten Burstedde, Jose A. Fonseca, Stefan Kollet

    Abstract: Regional hydrology studies are often supported by high resolution simulations of subsurface flow that require expensive and extensive computations. Efficient usage of the latest high performance parallel computing systems becomes a necessity. The simulation software ParFlow has been demonstrated to meet this requirement and shown to have excellent solver scalability for up to 16,384 processes. In… ▽ More

    Submitted 2 October, 2017; v1 submitted 22 February, 2017; originally announced February 2017.

    Comments: The final publication is available at link.springer.com

    Journal ref: Computational Geosciences 2017

  21. arXiv:1611.04529  [pdf, ps, other

    cs.SI physics.soc-ph

    Can information be spread as a virus? Viral Marketing as epidemiological model

    Authors: Helena Sofia Rodrigues, Manuel José Fonseca

    Abstract: In epidemiology, an epidemic is defined as the spread of an infectious disease to a large number of people in a given population within a short period of time. In the marketing context, a message is viral when it is broadly sent and received by the target market through person-to-person transmission. This specific marketing communication strategy is commonly referred as viral marketing. Due to thi… ▽ More

    Submitted 8 November, 2016; originally announced November 2016.

    Comments: Please cite this paper as: Rodrigues, Helena Sofia and Fonseca, Manuel José (2016) . Can information be spread as a virus? Viral Marketing as epidemiological model, Mathematical Methods in the Applied Sciences, 39: 4780--4786. arXiv admin note: substantial text overlap with arXiv:1507.06986

    MSC Class: 34A34; 92D30; 91F99

    Journal ref: Mathematical Methods in the Applied Sciences,39: 4780--4786, 2016

  22. arXiv:1510.04686  [pdf

    cs.DC physics.comp-ph

    NEMO5: Achieving High-end Internode Communication for Performance Projection Beyond Moore's Law

    Authors: Robert Andrawis, Jose David Bermeo, James Charles, Jianbin Fang, Jim Fonseca, Yu He, Gerhard Klimeck, Zhengping Jiang, Tillmann Kubis, Daniel Mejia, Daniel Lemus, Michael Povolotskyi, Santiago Alonso Perez Rubiano, Prasad Sarangapani, Lang Zeng

    Abstract: Electronic performance predictions of modern nanotransistors require nonequilibrium Green's functions including incoherent scattering on phonons as well as inclusion of random alloy disorder and surface roughness effects. The solution of all these effects is numerically extremely expensive and has to be done on the world's largest supercomputers due to the large memory requirement and the high per… ▽ More

    Submitted 15 October, 2015; originally announced October 2015.

  23. arXiv:1510.04233  [pdf, other

    cs.DC

    Arabesque: A System for Distributed Graph Mining - Extended version

    Authors: Carlos H. C. Teixeira, Alexandre J. Fonseca, Marco Serafini, Georgos Siganos, Mohammed J. Zaki, Ashraf Aboulnaga

    Abstract: Distributed data processing platforms such as MapReduce and Pregel have substantially simplified the design and deployment of certain classes of distributed graph analytics algorithms. However, these platforms do not represent a good match for distributed graph mining problems, as for example finding frequent subgraphs in a graph. Given an input graph, these problems require exploring a very large… ▽ More

    Submitted 14 October, 2015; originally announced October 2015.

    Comments: A short version of this report appeared in the Proceedings of the 25th ACM Symp. on Operating Systems Principles (SOSP), 2015

    Report number: QCRI-TR-2015-005

  24. arXiv:1507.06986  [pdf, other

    physics.soc-ph cs.SI

    Viral marketing as epidemiological model

    Authors: Helena Sofia Rodrigues, Manuel José Fonseca

    Abstract: In epidemiology, an epidemic is defined as the spread of an infectious disease to a large number of people in a given population within a short period of time. In the marketing context, a message is viral when it is broadly sent and received by the target market through person-to-person transmission. This specific marketing communication strategy is commonly referred as viral marketing. Due to thi… ▽ More

    Submitted 24 July, 2015; originally announced July 2015.

    Comments: This is a preprint of a paper whose final and definite form is in Proceedings of the 15th International Conference on Computational and Mathematical Methods in Science and Engineering, 2015, pages 946 - 955

    MSC Class: 34A34; 92D30; 91F99

  25. arXiv:1412.5557  [pdf

    cs.DC

    Standing Together for Reproducibility in Large-Scale Computing: Report on reproducibility@XSEDE

    Authors: Doug James, Nancy Wilkins-Diehr, Victoria Stodden, Dirk Colbry, Carlos Rosales, Mark Fahey, Justin Shi, Rafael F. Silva, Kyo Lee, Ralph Roskies, Laurence Loewe, Susan Lindsey, Rob Kooper, Lorena Barba, David Bailey, Jonathan Borwein, Oscar Corcho, Ewa Deelman, Michael Dietze, Benjamin Gilbert, Jan Harkes, Seth Keele, Praveen Kumar, Jong Lee, Erika Linke , et al. (30 additional authors not shown)

    Abstract: This is the final report on reproducibility@xsede, a one-day workshop held in conjunction with XSEDE14, the annual conference of the Extreme Science and Engineering Discovery Environment (XSEDE). The workshop's discussion-oriented agenda focused on reproducibility in large-scale computational research. Two important themes capture the spirit of the workshop submissions and discussions: (1) organiz… ▽ More

    Submitted 2 January, 2015; v1 submitted 17 December, 2014; originally announced December 2014.

    MSC Class: 68N01 ACM Class: D.2.9

  26. arXiv:1004.0774  [pdf

    cs.SE cs.CR cs.NI

    A security framework for SOA applications in mobile environment

    Authors: Johnneth Fonseca, Zair Abdelouahab, Denivaldo Lopes, Sofiane Labidi

    Abstract: A Rapid evolution of mobile technologies has led to the development of more sophisticated mobile devices with better storage, processing and transmission power. These factors enable support to many types of application but also give rise to a necessity to find a model of service development. Actually, SOA (Service Oriented Architecture) is a good option to support application development. This pap… ▽ More

    Submitted 6 April, 2010; originally announced April 2010.

    Comments: 18Pages

    Journal ref: International Journal of Network Security & Its Applications 1.3 (2009) 90-107