Samira Ebrahimi Kahou

PhD - McGill University

Co-supervisor :

Master's Research - École de technologie suprérieure

Website

Google Scholar

Priyesh Vijayan

PhD - McGill University

Principal supervisor :

Publications

Prioritizing Samples in Reinforcement Learning with Reducible Loss

Shiva Kanth Sujit

Pedro Braga

Fairness Under Demographic Scarce Regime

Patrik Joslin Kenfack

Ulrich Aivodji

Most existing works on fairness assume the model has full access to demographic information. However, there exist scenarios where demographi… (see more)c information is partially available because a record was not maintained throughout data collection or due to privacy reasons. This setting is known as demographic scarce regime. Prior research have shown that training an attribute classifier to replace the missing sensitive attributes (proxy) can still improve fairness. However, the use of proxy-sensitive attributes worsens fairness-accuracy trade-offs compared to true sensitive attributes. To address this limitation, we propose a framework to build attribute classifiers that achieve better fairness-accuracy trade-offs. Our method introduces uncertainty awareness in the attribute classifier and enforces fairness on samples with demographic information inferred with the lowest uncertainty. We show empirically that enforcing fairness constraints on samples with uncertain sensitive attributes is detrimental to fairness and accuracy. Our experiments on two datasets showed that the proposed framework yields models with significantly better fairness-accuracy trade-offs compared to classic attribute classifiers. Surprisingly, our framework outperforms models trained with constraints on the true sensitive attributes.

2023-07-24

ArXiv (preprint)

Transformers in Reinforcement Learning: A Survey

Pranav Agarwal

Aamer Abdul Rahman

Pierre-Luc St-Charles

Simon J. D. Prince

Transformers have significantly impacted domains like natural language processing, computer vision, and robotics, where they improve perform… (see more)ance compared to other neural networks. This survey explores how transformers are used in reinforcement learning (RL), where they are seen as a promising solution for addressing challenges such as unstable training, credit assignment, lack of interpretability, and partial observability. We begin by providing a brief domain overview of RL, followed by a discussion on the challenges of classical RL algorithms. Next, we delve into the properties of the transformer and its variants and discuss the characteristics that make them well-suited to address the challenges inherent in RL. We examine the application of transformers to various aspects of RL, including representation learning, transition and reward function modeling, and policy optimization. We also discuss recent research that aims to enhance the interpretability and efficiency of transformers in RL, using visualization techniques and efficient training strategies. Often, the transformer architecture must be tailored to the specific needs of a given application. We present a broad overview of how transformers have been adapted for several applications, including robotics, medicine, language modeling, cloud computing, and combinatorial optimization. We conclude by discussing the limitations of using transformers in RL and assess their potential for catalyzing future breakthroughs in this field.

2023-07-12

ArXiv (preprint)

arxiv.org

Discovering Object-Centric Generalized Value Functions From Pixels

Gopeshh Subbaraj

Khimya Khetarpal

Deep Reinforcement Learning has shown significant progress in extracting useful representations from high-dimensional inputs albeit using ha… (see more)nd-crafted auxiliary tasks and pseudo rewards. Automatically learning such representations in an object-centric manner geared towards control and fast adaptation remains an open research problem. In this paper, we introduce a method that tries to discover meaningful features from objects, translating them to temporally coherent"question"functions and leveraging the subsequent learned general value functions for control. We compare our approach with state-of-the-art techniques alongside other ablations and show competitive performance in both stationary and non-stationary settings. Finally, we also investigate the discovered general value functions and through qualitative analysis show that the learned representations are not only interpretable but also, centered around objects that are invariant to changes across tasks facilitating fast adaptation.

2023-07-03

Proceedings of the 40th International Conference on Machine Learning (published)

CAMMARL: Conformal Action Modeling in Multi Agent Reinforcement Learning

Nikunj Gupta

Before taking actions in an environment with more than one intelligent agent, an autonomous agent may benefit from reasoning about the other… (see more) agents and utilizing a notion of a guarantee or confidence about the behavior of the system. In this article, we propose a novel multi-agent reinforcement learning (MARL) algorithm CAMMARL, which involves modeling the actions of other agents in different situations in the form of confident sets, i.e., sets containing their true actions with a high probability. We then use these estimates to inform an agent's decision-making. For estimating such sets, we use the concept of conformal predictions, by means of which, we not only obtain an estimate of the most probable outcome but get to quantify the operable uncertainty as well. For instance, we can predict a set that provably covers the true predictions with high probabilities (e.g., 95%). Through several experiments in two fully cooperative multi-agent tasks, we show that CAMMARL elevates the capabilities of an autonomous agent in MARL by modeling conformal prediction sets over the behavior of other agents in the environment and utilizing such estimates to enhance its policy learning.

2023-06-19

ArXiv (preprint)

Overcoming Interpretability and Accuracy Trade-off in Medical Imaging

Ivaxi Sheth

2023-04-28

MIDL.io/2023/Short_Paper_Track (poster)

Source-free Domain Adaptation Requires Penalized Diversity

Laya Rafiee Sevyeri

Ivaxi Sheth

Farhood Farahnak

Alexandre See

Thomas Fevens

Mohammad Havaei

While neural networks are capable of achieving human-like performance in many tasks such as image classification, the impressive performance… (see more) of each model is limited to its own dataset. Source-free domain adaptation (SFDA) was introduced to address knowledge transfer between different domains in the absence of source data, thus, increasing data privacy. Diversity in representation space can be vital to a model`s adaptability in varied and difficult domains. In unsupervised SFDA, the diversity is limited to learning a single hypothesis on the source or learning multiple hypotheses with a shared feature extractor. Motivated by the improved predictive performance of ensembles, we propose a novel unsupervised SFDA algorithm that promotes representational diversity through the use of separate feature extractors with Distinct Backbone Architectures (DBA). Although diversity in feature space is increased, the unconstrained mutual information (MI) maximization may potentially introduce amplification of weak hypotheses. Thus we introduce the Weak Hypothesis Penalization (WHP) regularizer as a mitigation strategy. Our work proposes Penalized Diversity (PD) where the synergy of DBA and WHP is applied to unsupervised source-free domain adaptation for covariate shift. In addition, PD is augmented with a weighted MI maximization objective for label distribution shift. Empirical results on natural, synthetic, and medical domains demonstrate the effectiveness of PD under different distributional shifts.

2023-04-06

ArXiv (preprint)

arxiv.org

Auxiliary Losses for Learning Generalizable Concept-based Models

Ivaxi Sheth

Learning from uncertain concepts via test time interventions

Ivaxi Sheth

Aamer Abdul Rahman

Laya Rafiee Sevyeri

Mohammad Havaei

With neural networks applied to safety-critical applications, it has become increasingly important to understand the defining features of de… (see more)cision-making. Therefore, the need to uncover the black boxes to rational representational space of these neural networks is apparent. Concept bottleneck model (CBM) encourages interpretability by predicting human-understandable concepts. They predict concepts from input images and then labels from concepts. Test time intervention, a salient feature of CBM, allows for human-model interactions. However, these interactions are prone to information leakage and can often be ineffective inappropriate communication with humans. We propose a novel uncertainty based strategy, \emph{SIUL: Single Interventional Uncertainty Learning} to select the interventions. Additionally, we empirically test the robustness of CBM and the effect of SIUL interventions under adversarial attack and distributional shift. Using SIUL, we observe that the interventions suggested lead to meaningful corrections along with mitigation of concept leakage. Extensive experiments on three vision datasets along with a histopathology dataset validate the effectiveness of our interventional learning.

2022-11-20

NeurIPS.cc/2022/Workshop/TSRML (accepted)

Learning Latent Structural Causal Models

Jithendaraa Subramanian

Yashas Annadani

Ivaxi Sheth

Nan Rosemary Ke

Tristan Deleu

Stefan Bauer

Derek Nowrouzezahrai

Causal learning has long concerned itself with the accurate recovery of underlying causal mechanisms. Such causal modelling enables better e… (see more)xplanations of out-of-distribution data. Prior works on causal learning assume that the high-level causal variables are given. However, in machine learning tasks, one often operates on low-level data like image pixels or high-dimensional vectors. In such settings, the entire Structural Causal Model (SCM) -- structure, parameters, \textit{and} high-level causal variables -- is unobserved and needs to be learnt from low-level data. We treat this problem as Bayesian inference of the latent SCM, given low-level data. For linear Gaussian additive noise SCMs, we present a tractable approximate inference method which performs joint inference over the causal variables, structure and parameters of the latent SCM from random, known interventions. Experiments are performed on synthetic datasets and a causally generated image dataset to demonstrate the efficacy of our approach. We also perform image generation from unseen interventions, thereby verifying out of distribution generalization for the proposed causal model.

2022-10-24

ArXiv (preprint)

Revisiting Learnable Affines for Batch Norm in Few-Shot Transfer Learning

Christian Desrosiers

Batch normalization is a staple of computer vision models, including those employed in few-shot learning. Batch nor-malization layers in con… (see more)volutional neural networks are composed of a normalization step, followed by a shift and scale of these normalized features applied via the per-channel trainable affine parameters

2022-06-18

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (published)

Latent Variable Sequential Set Transformers for Joint Multi-Agent Motion Prediction

Jim Aldon D'Souza

Felix Heide

Chris Pal

Robust multi-agent trajectory prediction is essential for the safe control of robotic systems. A major challenge is to efficiently learn a r… (see more)epresentation that approximates the true joint distribution of contextual, social, and temporal information to enable planning. We propose Latent Variable Sequential Set Transformers which are encoder-decoder architectures that generate scene-consistent multi-agent trajectories. We refer to these architectures as “AutoBots”. The encoder is a stack of interleaved temporal and social multi-head self-attention (MHSA) modules which alternately perform equivariant processing across the temporal and social dimensions. The decoder employs learnable seed parameters in combination with temporal and social MHSA modules allowing it to perform inference over the entire future scene in a single forward pass efficiently. AutoBots can produce either the trajectory of one ego-agent or a distribution over the future trajectories for all agents in the scene. For the single-agent prediction case, our model achieves top results on the global nuScenes vehicle motion prediction leaderboard, and produces strong results on the Argoverse vehicle prediction challenge. In the multi-agent setting, we evaluate on the synthetic partition of TrajNet++ dataset to showcase the model’s socially-consistent predictions. We also demonstrate our model on general sequences of sets and provide illustrative experiments modelling the sequential structure of the multiple strokes that make up symbols in the Omniglot data. A distinguishing feature of AutoBots is that all models are trainable on a single desktop GPU (1080 Ti) in under 48h.

2022-01-01

ICLR (published)