Portrait de Samira Ebrahimi Kahou

Samira Ebrahimi Kahou

Membre affilié
Professeure agrégée, University of Calgary
Professeure associée, École de technologie suprérieure, Département de génie logiciel et technologies de l'information
Professeure associée, McGill University, École d'informatique
Sujets de recherche
Apprentissage automatique médical
Apprentissage de représentations
Apprentissage multimodal
Apprentissage par renforcement
Apprentissage profond
Traitement du langage naturel
Vision par ordinateur

Biographie

Samira est professeure agrégée à l’Université de Calgary, à la Schulich School of Engineering. Elle est également professeure associée à l’École de technologie supérieure (ÉTS), au Département de génie logiciel et des technologies de l’information, ainsi qu’à l’Université McGill, à l’École d’informatique. Elle est membre académique de Mila - Institut québécois d’intelligence artificielle et détient une Chaire canadienne CIFAR en IA. Samira a obtenu son doctorat en génie informatique à Polytechnique Montréal/Mila, avec un prix pour la meilleure thèse du département. Elle a également travaillé comme chercheuse postdoctorale à l’École d’informatique de l’Université McGill et comme chercheuse à Microsoft Research Montréal.

Samira et son groupe de recherche travaillent à résoudre des problèmes fondamentaux de l’apprentissage de représentations pour la prise de décision, avec un accent particulier sur l’explicabilité, la généralisation et l’apprentissage efficace. Ses travaux ont été publiés dans des conférences et revues de premier plan telles que NeurIPS, ICLR, ICML, ICCV, CVPR, TMLR et CoRL. Samira a reçu en 2024 le prix d’excellence en recherche en début de carrière de la Schulich School of Engineering. Ses contributions marquantes en apprentissage multimodal ont été reconnues à deux reprises par les prix ACM ICMI Ten-Year Technical Impact Awards : finaliste en 2023 et lauréate en 2025.

Étudiants actuels

Doctorat - UdeM
Superviseur⋅e principal⋅e :
Doctorat - École de technologie suprérieure
Superviseur⋅e principal⋅e :
Doctorat - École de technologie suprérieure
Superviseur⋅e principal⋅e :
Doctorat - McGill
Superviseur⋅e principal⋅e :

Billets de blogue

par
Ankur Garg
Xuemin Yu
Hassan Sajjad

Publications

Survey on <scp>AI</scp> Ethics: A Socio‐Technical Perspective
Dave Mbiazi
Ivaxi Sheth
Patrik Joslin Kenfack
Abstract The past decade has observed a significant advancement in AI, with deep learning‐based models being deployed in diverse scenarios… (voir plus), including safety‐critical applications. As these AI systems become deeply embedded in our societal infrastructure, the repercussions of their decisions and actions have significant consequences, making the ethical implications of AI deployment highly relevant and essential. The ethical concerns associated with AI are multifaceted, including challenging issues of fairness, privacy and data protection, responsibility and accountability, safety and robustness, transparency and explainability, and environmental impact. These principles together form the foundations of ethical AI considerations that concern every stakeholder in the AI system lifecycle. In light of the present ethical and future x‐risk concerns, governments have shown increasing interest in establishing guidelines for the ethical deployment of AI. This work unifies the current and future ethical concerns of deploying AI into society. While we acknowledge and appreciate the technical surveys for each of the ethical principles concerned, in this paper, we aim to provide a comprehensive overview that not only addresses each principle from a technical point of view but also discusses them from a social perspective.
Handling Delay in Real-Time Reinforcement Learning
Real-time reinforcement learning (RL) introduces several challenges. First, policies are constrained to a fixed number of actions per second… (voir plus) due to hardware limitations. Second, the environment may change while the network is still computing an action, leading to observational delay. The first issue can partly be addressed with pipelining, leading to higher throughput and potentially better policies. However, the second issue remains: if each neuron operates in parallel with an execution time of
Adaptive Group Robust Ensemble Knowledge Distillation
Patrik Joslin Kenfack
Neural networks can learn spurious correlations in the data, often leading to performance disparity for underrepresented subgroups. Studies … (voir plus)have demonstrated that the disparity is amplified when knowledge is distilled from a complex teacher model to a relatively"simple"student model. Prior work has shown that ensemble deep learning methods can improve the performance of the worst-case subgroups; however, it is unclear if this advantage carries over when distilling knowledge from an ensemble of teachers, especially when the teacher models are debiased. This study demonstrates that traditional ensemble knowledge distillation can significantly drop the performance of the worst-case subgroups in the distilled student model even when the teacher models are debiased. To overcome this, we propose Adaptive Group Robust Ensemble Knowledge Distillation (AGRE-KD), a simple ensembling strategy to ensure that the student model receives knowledge beneficial for unknown underrepresented subgroups. Leveraging an additional biased model, our method selectively chooses teachers whose knowledge would better improve the worst-performing subgroups by upweighting the teachers with gradient directions deviating from the biased model. Our experiments on several datasets demonstrate the superiority of the proposed ensemble distillation technique and show that it can even outperform classic model ensembles based on majority voting.
Attention-Based Multi-Agent RL for Multi-Machine Tending Using Mobile Robots
Abdalwhab Bakheet Mohamed Abdalwhab
David St-Onge
Robotics can help address the growing worker shortage challenge of the manufacturing industry. As such, machine tending is a task collaborat… (voir plus)ive robots can tackle that can also greatly boost productivity. Nevertheless, existing robotics systems deployed in that sector rely on a fixed single-arm setup, whereas mobile robots can provide more flexibility and scalability. We introduce a multi-agent multi-machine-tending learning framework using mobile robots based on multi-agent reinforcement learning (MARL) techniques, with the design of a suitable observation and reward. Moreover, we integrate an attention-based encoding mechanism into the Multi-Agent Proximal Policy Optimization (MAPPO) algorithm to boost its performance for machine-tending scenarios. Our model (AB-MAPPO) outperforms MAPPO in this new challenging scenario in terms of task success, safety, and resource utilization. Furthermore, we provided an extensive ablation study to support our design decisions.
Source-free Domain Adaptation Requires Penalized Diversity
While neural networks are capable of achieving human-like performance in many tasks such as image classification, the impressive performance… (voir plus) 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.
Learning to Play Atari in a World of Tokens
Model-based reinforcement learning agents utilizing transformers have shown improved sample efficiency due to their ability to model extende… (voir plus)d context, resulting in more accurate world models. However, for complex reasoning and planning tasks, these methods primarily rely on continuous representations. This complicates modeling of discrete properties of the real world such as disjoint object classes between which interpolation is not plausible. In this work, we introduce discrete abstract representations for transformer-based learning (DART), a sample-efficient method utilizing discrete representations for modeling both the world and learning behavior. We incorporate a transformer-decoder for auto-regressive world modeling and a transformer-encoder for learning behavior by attending to task-relevant cues in the discrete representation of the world model. For handling partial observability, we aggregate information from past time steps as memory tokens. DART outperforms previous state-of-the-art methods that do not use look-ahead search on the Atari 100k sample efficiency benchmark with a median human-normalized score of 0.790 and beats humans in 9 out of 26 games. We release our code at https://pranaval.github.io/DART/.
On the Limits of Multi-modal Meta-Learning with Auxiliary Task Modulation Using Conditional Batch Normalization
Few-shot learning aims to learn representations that can tackle novel tasks given a small number of examples. Recent studies show that cross… (voir plus)-modal learning can improve representations for few-shot classification. More specifically, language is a rich modality that can be used to guide visual learning. In this work, we experiment with a multi-modal architecture for few-shot learning that consists of three components: a classifier, an auxiliary network, and a bridge network. While the classifier performs the main classification task, the auxiliary network learns to predict language representations from the same input, and the bridge network transforms high-level features of the auxiliary network into modulation parameters for layers of the few-shot classifier using conditional batch normalization. The bridge should encourage a form of lightweight semantic alignment between language and vision which could be useful for the classifier. However, after evaluating the proposed approach on two popular few-shot classification benchmarks we find that a) the improvements do not reproduce across benchmarks, and b) when they do, the improvements are due to the additional compute and parameters introduced by the bridge network. We contribute insights and recommendations for future work in multi-modal meta-learning, especially when using language representations.
Prioritizing Samples in Reinforcement Learning with Reducible Loss
Most reinforcement learning algorithms take advantage of an experience replay buffer to repeatedly train on samples the agent has observed i… (voir plus)n the past. Not all samples carry the same amount of significance and simply assigning equal importance to each of the samples is a naïve strategy. In this paper, we propose a method to prioritize samples based on how much we can learn from a sample. We define the learn-ability of a sample as the steady decrease of the training loss associated with this sample over time. We develop an algorithm to prioritize samples with high learn-ability, while assigning lower priority to those that are hard-to-learn, typically caused by noise or stochasticity. We empirically show that our method is more robust than random sampling and also better than just prioritizing with respect to the training loss, i.e. the temporal difference loss, which is used in prioritized experience replay.
Spectral Temporal Contrastive Learning
Learning useful data representations without requiring labels is a cornerstone of modern deep learning. Self-supervised learning methods, pa… (voir plus)rticularly contrastive learning (CL), have proven successful by leveraging data augmentations to define positive pairs. This success has prompted a number of theoretical studies to better understand CL and investigate theoretical bounds for downstream linear probing tasks. This work is concerned with the temporal contrastive learning (TCL) setting where the sequential structure of the data is used instead to define positive pairs, which is more commonly used in RL and robotics contexts. In this paper, we adapt recent work on Spectral CL to formulate Spectral Temporal Contrastive Learning (STCL). We discuss a population loss based on a state graph derived from a time-homogeneous reversible Markov chain with uniform stationary distribution. The STCL loss enables to connect the linear probing performance to the spectral properties of the graph, and can be estimated by considering previously observed data sequences as an ensemble of MCMC chains.
Discovering Object-Centric Generalized Value Functions From Pixels
Deep Reinforcement Learning has shown significant progress in extracting useful representations from high-dimensional inputs albeit using ha… (voir plus)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.
From legacy to microservices: A type-based approach for microservices identification using machine learning and semantic analysis.
Imen Trabelsi
Manel Abdellatif
Naouel Moha
Sébastien Mosser
Yann-Gaël Guéhéneuc
The microservices architecture (MSA) style has been gaining interest in recent years because of its high scalability, ability to be deployed… (voir plus) in the cloud, and suitability for DevOps practices. While new applications can adopt MSA from their inception, many legacy monolithic systems must be migrated to an MSA to benefit from the advantages of this architectural style. To support the migration process, we propose MicroMiner, a microservices identification approach that is based on static‐relationship analyses between code elements as well as semantic analyses of the source code. Our approach relies on machine learning (ML) techniques and uses service types to guide the identification of microservices from legacy monolithic systems. We evaluate the efficiency of our approach on four systems and compare our results to ground‐truths and to those of two state‐of‐the‐art approaches. We perform a qualitative evaluation of the resulted microservices by analyzing the business capabilities of the identified microservices. Also a quantitative analysis using the state‐of‐the‐art metrics on independence of functionality and modularity of services was conducted. Our results show the effectiveness of our approach to automate one of the most time‐consuming steps in the migration of legacy systems to microservices. The proposed approach identifies architecturally significant microservices with a 68.15% precision and 77% recall.
Learning Latent Structural Causal Models
Causal learning has long concerned itself with the accurate recovery of underlying causal mechanisms. Such causal modelling enables better e… (voir plus)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.