Publications

A Novel Information-Theoretic Objective to Disentangle Representations for Fair Classification

Pierre Colombo

Nathan Noiry

Guillaume Staerman

Pablo Piantanida

2023-10-21

ArXiv (prépublication)

doi.org

arxiv.org

Fundamental Limits of Membership Inference Attacks on Machine Learning Models

Eric Aubinais

Elisabeth Gassiat

Pablo Piantanida

Membership inference attacks (MIA) can reveal whether a particular data point was part of the training dataset, potentially exposing sensiti… (voir plus)ve information about individuals. This article provides theoretical guarantees by exploring the fundamental statistical limitations associated with MIAs on machine learning models. More precisely, we first derive the statistical quantity that governs the effectiveness and success of such attacks. We then deduce that in a very general regression setting with overfitting algorithms, attacks may have a high probability of success. Finally, we investigate several situations for which we provide bounds on this quantity of interest. Our results enable us to deduce the accuracy of potential attacks based on the number of samples and other structural parameters of learning models. In certain instances, these parameters can be directly estimated from the dataset.

2023-10-20

ArXiv (prépublication)

doi.org

arxiv.org

Surprise-Adaptive Intrinsic Motivation for Unsupervised Reinforcement Learning

Adriana Hugessen

Roger Creus Castanyer

Glen Berseth

2023-10-20

NeurIPS.cc/2023/Workshop/IMOL (présentation orale)

openreview.net

Detection and evaluation of bias-inducing features in machine learning

Moses Openja

gabriel laberge

Foutse Khomh

2023-10-19

ArXiv (prépublication)

doi.org

arxiv.org

Graph embedding and transfer learning can help predict potential species interaction networks despite data limitations

Tanya Strydom

Salomé Bouskila

Francis Banville

Ceres Barros

Dominique Caron

Maxwell J. Farrell

Marie‐Josée Fortin

Benjamin Mercier

Laura J. Pollock

Rogini Runghen

Giulio V. Dalla Riva

Timothée Poisot

Metawebs (networks of potential interactions within a species pool) are a powerful abstraction to understand how large‐scale species inter… (voir plus)action networks are structured. Because metawebs are typically expressed at large spatial and taxonomic scales, assembling them is a tedious and costly process; predictive methods can help circumvent the limitations in data deficiencies, by providing a first approximation of metawebs. One way to improve our ability to predict metawebs is to maximize available information by using graph embeddings, as opposed to an exhaustive list of species interactions. Graph embedding is an emerging field in machine learning that holds great potential for ecological problems. Here, we outline how the challenges associated with inferring metawebs line‐up with the advantages of graph embeddings; followed by a discussion as to how the choice of the species pool has consequences on the reconstructed network, specifically as to the role of human‐made (or arbitrarily assigned) boundaries and how these may influence ecological hypotheses.

2023-10-19

Methods in Ecology and Evolution (publié)

doi.org

Mean-field games among teams

Jayakumar Subramanian

Akshat Kumar

Aditya Mahajan

2023-10-18

ArXiv (prépublication)

doi.org

arxiv.org

A Persuasive Approach to Combating Misinformation

Safwan Hossain

Andjela Mladenovic

Yiling Chen

Gauthier Gidel

Bayesian Persuasion is proposed as a tool for social media platforms to combat the spread of misinformation. Since platforms can use machine… (voir plus) learning to predict the popularity and misinformation features of to-be-shared posts, and users are largely motivated to share popular content, platforms can strategically signal this informational advantage to change user beliefs and persuade them not to share misinformation. We characterize the optimal signaling scheme with imperfect predictions as a linear program and give sufficient and necessary conditions on the classifier to ensure optimal platform utility is non-decreasing and continuous. Next, this interaction is considered under a performative model, wherein platform intervention affects the user's future behaviour. The convergence and stability of optimal signaling under this performative process are fully characterized. Lastly, we experimentally validate that our approach significantly reduces misinformation in both the single round and performative setting and discuss the broader scope of using information design to combat misinformation.

2023-10-18

ArXiv (prépublication)

doi.org

arxiv.org

Studying the characteristics of AIOps projects on GitHub

Roozbeh Aghili

Heng Li

Foutse Khomh

2023-10-18

Empirical Software Engineering (publié)

doi.org

arxiv.org