Publications

Leveraging Data Mining Algorithms to Recommend Source Code Changes
AmirHossein Naghshzan
Saeed Khalilazar
Pierre Poilane
Olga Baysal
Latifa Guerrouj
Foutse Khomh
2023-04-28
ArXiv (prépublication)
doi.org
arxiv.org
Group Fairness in Reinforcement Learning
Harsh Satija
Alessandro Lazaric
Matteo Pirotta
Joelle Pineau
We pose and study the problem of satisfying fairness in the online Reinforcement Learning (RL) setting. We focus on the group notions of fai… (voir plus)rness, according to which agents belonging to different groups should have similar performance based on some given measure. We consider the setting of maximizing return in an unknown environment (unknown transition and reward function) and show that it is possible to have RL algorithms that learn the best fair policies without violating the fairness requirements at any point in time during the learning process. In the tabular finite-horizon episodic setting, we provide an algorithm that combines the principle of optimism and pessimism under uncertainty to achieve zero fairness violation with arbitrarily high probability while also maintaining sub-linear regret guarantees. For the high-dimensional Deep-RL setting, we present algorithms based on the performance-difference style approximate policy improvement update step and we report encouraging empirical results on various traditional RL-inspired benchmarks showing that our algorithms display the desired behavior of learning the optimal policy while performing a fair learning process.
2023-04-27
TMLR (accepté)
openreview.net
openreview.net
Overcoming Interpretability and Accuracy Trade-off in Medical Imaging
Ivaxi Sheth
S Ebrahimi Kahou
2023-04-27
MIDL.io/2023/Short_Paper_Track (poster)
openreview.net
openreview.net
Use of Invasive Brain-Computer Interfaces in Pediatric Neurosurgery: Technical and Ethical Considerations
David Bergeron
Christian Iorio-Morin
Marco Bonizzato
Guillaume Lajoie
Nathalie Orr Gaucher
Éric Racine
Alexander G. Weil
2023-04-27
Journal of Child Neurology (publié)
doi.org
Lightweight, Pre-trained Transformers for Remote Sensing Timeseries
Gabriel Tseng
Ivan Zvonkov
Ruben Cartuyvels
Mirali Purohit
David Rolnick
Hannah Kerner
Machine learning methods for satellite data have a range of societally relevant applications, but labels used to train models can be difficu… (voir plus)lt or impossible to acquire. Self-supervision is a natural solution in settings with limited labeled data, but current self-supervised models for satellite data fail to take advantage of the characteristics of that data, including the temporal dimension (which is critical for many applications, such as monitoring crop growth) and availability of data from many complementary sensors (which can significantly improve a model's predictive performance). We present Presto (the Pretrained Remote Sensing Transformer), a model pre-trained on remote sensing pixel-timeseries data. By designing Presto specifically for remote sensing data, we can create a significantly smaller but performant model. Presto excels at a wide variety of globally distributed remote sensing tasks and performs competitively with much larger models while requiring far less compute. Presto can be used for transfer learning or as a feature extractor for simple models, enabling efficient deployment at scale.
2023-04-26
ArXiv (prépublication)
doi.org
openreview.net
The Influence of Age, Sex, and Socioeconomic Status on Glycemic Control Among People With Type 1 and Type 2 Diabetes in Canada: Patient-Led Longitudinal Retrospective Cross-sectional Study With Multiple Time Points of Measurement
Seyedmostafa Mousavi
Dana Tannenbaum Greenberg
Ruth Ndjaboué
Michelle Greiver
Olivia Drescher
Selma Chipenda Dansokho
Denis Boutin
Jean-Marc Chouinard
Sylvie Dostie
Robert Fenton
Marley Greenberg
Jonathan McGavock
Adhiyat Najam
Monia Rekik
Tom Weisz
Donald J Willison
Audrey Durand
Holly O Witteman
2023-04-26
JMIR Diabetes (publié)
doi.org
Controllable Image Generation via Collage Representations
Arantxa Casanova
Marlene Careil
Adriana Romero
Christopher Pal
Jakob Verbeek
Michal Drozdzal
2023-04-25
ArXiv (prépublication)
doi.org
openreview.net
Towards ethical multimodal systems
Alexis Roger
Esma Aimeur
Irina Rish
2023-04-25
ArXiv (prépublication)
doi.org
arxiv.org
Tri-process model of interpersonal mindfulness: theoretical framework and study protocol
Bassam Khoury
Viktoriya Manova
Lena Adel
Guillaume Dumas
Michael Lifshitz
Rodrigo C. Vergara
Harmehr Sekhon
Soham Rej
According to the Center for Disease Control and Prevention, over 14% of the US population practice mindfulness meditation. The effects of mi… (voir plus)ndfulness training on physical and mental health have been consistently documented, but its effects on interpersonal relationships are not yet fully understood or investigated. Interpersonal relationships play a crucial role in the wellbeing of individuals and society, and therefore, warrants further study. The aim of this paper is to present a tri-process theoretical model of interpersonal mindfulness and a study protocol to validate the proposed model. Specifically, according to the proposed model, mindfulness meditation training increases the self-awareness, self-regulation, and prosociality of those receiving the training, which ameliorates the quality of interpersonal interactions and the socioemotional support provided to other individuals. Finally, better socioemotional support increases the support receiver’s ability to regulate their emotions. Using a multiphasic longitudinal design involving 640 participants randomized into 480 dyads, the proposed protocol aims to validate the tri-process model and to investigate its mechanisms of actions. The proposed study has important theoretical and social implications and will allow devising new and more effective interpersonal mindfulness programs with applications in multiple fields.
2023-04-25
Frontiers in Psychology (publié)
doi.org
Understanding the normative leadership of the world health organization (who): a mixed-method approach
Catherine Régis
Miriam Cohen
Jean-Louis Denis
Pierre Larouche
Gaëlle Foucault
Marie-Andree Girard
2023-04-25
Population Medicine (publié)
doi.org
Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation
Junde Wu
Rao Fu
Huihui Fang
Yuanpei Liu
Zhao-Yang Wang
Yanwu Xu
Yueming Jin
Tal Arbel
The Segment Anything Model (SAM) has recently gained popularity in the field of image segmentation due to its impressive capabilities in var… (voir plus)ious segmentation tasks and its prompt-based interface. However, recent studies and individual experiments have shown that SAM underperforms in medical image segmentation, since the lack of the medical specific knowledge. This raises the question of how to enhance SAM's segmentation capability for medical images. In this paper, instead of fine-tuning the SAM model, we propose the Medical SAM Adapter (Med-SA), which incorporates domain-specific medical knowledge into the segmentation model using a light yet effective adaptation technique. In Med-SA, we propose Space-Depth Transpose (SD-Trans) to adapt 2D SAM to 3D medical images and Hyper-Prompting Adapter (HyP-Adpt) to achieve prompt-conditioned adaptation. We conduct comprehensive evaluation experiments on 17 medical image segmentation tasks across various image modalities. Med-SA outperforms several state-of-the-art (SOTA) medical image segmentation methods, while updating only 2\% of the parameters. Our code is released at https://github.com/KidsWithTokens/Medical-SAM-Adapter.
2023-04-24
ArXiv (prépublication)
doi.org
arxiv.org
Performative Prediction with Neural Networks
Mehrnaz Mofakhami
Ioannis Mitliagkas
Gauthier Gidel
Performative prediction is a framework for learning models that influence the data they intend to predict. We focus on finding classifiers t… (voir plus)hat are performatively stable, i.e. optimal for the data distribution they induce. Standard convergence results for finding a performatively stable classifier with the method of repeated risk minimization assume that the data distribution is Lipschitz continuous to the model's parameters. Under this assumption, the loss must be strongly convex and smooth in these parameters; otherwise, the method will diverge for some problems. In this work, we instead assume that the data distribution is Lipschitz continuous with respect to the model's predictions, a more natural assumption for performative systems. As a result, we are able to significantly relax the assumptions on the loss function. In particular, we do not need to assume convexity with respect to the model's parameters. As an illustration, we introduce a resampling procedure that models realistic distribution shifts and show that it satisfies our assumptions. We support our theory by showing that one can learn performatively stable classifiers with neural networks making predictions about real data that shift according to our proposed procedure.
2023-04-24
International Conference on Artificial Intelligence and Statistics (Accept (Poster))
doi.org
proceedings.mlr.press