Samira Ebrahimi Kahou

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

Ivan Anokhin

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Irina Rish

ivan.anokhin@mila.quebec

Github

meghana.bhange@mila.quebec

Meghana Bhange

Doctorat - École de technologie suprérieure

Superviseur⋅e principal⋅e :

Ulrich Aivodji

Doctorat - École de technologie suprérieure

Superviseur⋅e principal⋅e :

Ulrich Aivodji

patrik.kenfack@mila.quebec

Site web

Github

Doctorat - McGill

Co-superviseur⋅e :

Derek Nowrouzezahrai

somjit.nath@mila.quebec

Site web

Faciliter l'audit des modèles de langage

Priyesh Vijayan

Doctorat - McGill

Superviseur⋅e principal⋅e :

Billets de blogue

Abstract digital visualization of layered, semi-transparent curved blue and purple panels featuring glowing lines of code, sparkling data points, and bokeh lights against a dark background.

7 août 2026

par

Ankur Garg

Xuemin Yu

Hassan Sajjad

Samira Ebrahimi Kahou

Lire l'article

Publications

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… (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.

2025-08-25

Machine Learning (publié)

Handling Delay in Real-Time Reinforcement Learning

Ivan Anokin

Rishav Rishav

Matthew Riemer

Stephen Chung

Irina Rish

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

2025-01-21

International Conference on Learning Representations (poster)

openreview.net

Learning to Play Atari in a World of Tokens

Pranav Agarwal

Sheldon Andrews

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/.

2024-07-22

International Conference on Machine Learning (Accept (Poster))

proceedings.mlr.press

On the Limits of Multi-modal Meta-Learning with Auxiliary Task Modulation Using Conditional Batch Normalization

Jordi Armengol-Estapé

Vincent Michalski

Ramnath Kumar

Pierre-Luc St-Charles

Doina Precup

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.

2023-12-31

Insights from Negative Results in NLP @ Association for Computational Linguistics (publié)

Prioritizing Samples in Reinforcement Learning with Reducible Loss

Shivakanth Sujit

Pedro H.M. Braga

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.

2023-12-11

Neural Information Processing Systems (Accept (poster))

openreview.net

Spectral Temporal Contrastive Learning

Sacha Morin

Guy Wolf

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.

2023-11-30

arXiv (prépublication)

Discovering Object-Centric Generalized Value Functions From Pixels

Gopeshh Raaj Subbaraj

Khimya Khetarpal

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.

2023-07-24

International Conference on Machine Learning (Accept (Poster))

proceedings.mlr.press

From legacy to microservices: A type-based approach for microservices identification using machine learning and semantic analysis.

Imen Trabelsi

Manel Abdellatif

Abdalgader Abubaker

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.

2022-12-31

Journal of Software: Evolution and Process (publié)

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… (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.

2022-10-23

arXiv (prépublication)

openreview.net

Towards Policy-Guided Conversational Recommendation with Dialogue Acts

Paul Crook

Y-Lan Boureau

J. Weston

Akbar Karimi

Leonardo Rossi

Andrea Prati

Wenqiang Lei

Xiangnan He

Qingyun Yisong Miao

Richang Wu

Min-Yen Hong

Kan Tat-Seng

Raymond Li

Hannes Schulz

Zujie Liang

Huang Hu

Can Xu

Jian Miao

Lizi Liao … (voir 47 de plus)

Ryuichi Takanobu

Yunshan Ma

Xun Yang

Wenchang Ma

Minlie Huang

Minghao Tu

Iulian Serban

Aaron C. Courville

David Silver

Julian Schrittwieser

K. Simonyan

Ioannis Antonoglou

Aja Huang

A. Guez

Hanlin Zhu

O. Vinyals

Igor Babuschkin

Junyoung Chung

M. Mathieu

Max Jaderberg

Wojciech M. Czar-725 necki

A. Dudzik

Petko Georgiev

Richard Powell

T. Ewalds

Dan Horgan

M. Kroiss

Ivo Danihelka

J. Agapiou

Junhyuk Oh

Valentin Dalibard

David Choi

L. Sifre

Yury Sulsky

Sasha Vezhnevets

James Molloy

Trevor Cai

D. Budden

T. Paine

Caglar Gulçehre

Ziyu Wang

Tobias Pfaff

Tobias Pohlen

2021-12-31

(publié)

www.semanticscholar.org

Simple Video Generation using Neural ODEs

David Kanaa

Vikram Voleti

Christopher Pal

Despite having been studied to a great extent, the task of conditional generation of sequences of frames, or videos, remains extremely chall… (voir plus)enging. It is a common belief that a key step towards solving this task resides in modelling accurately both spatial and temporal information in video signals. A promising direction to do so has been to learn latent variable models that predict the future in latent space and project back to pixels, as suggested in recent literature. Following this line of work and building on top of a family of models introduced in prior work, Neural ODE, we investigate an approach that models time-continuous dynamics over a continuous latent space with a differential equation with respect to time. The intuition behind this approach is that these trajectories in latent space could then be extrapolated to generate video frames beyond the time steps for which the model is trained. We show that our approach yields promising results in the task of future frame prediction on the Moving MNIST dataset with 1 and 2 digits.

2021-09-06

arXiv (prépublication)

Accounting for Variance in Machine Learning Benchmarks

Mirko Bronzi

Naz Sepah

Edward Raff

Kanika Madan

Vikram Voleti

Strong empirical evidence that one machine-learning algorithm A outperforms another one B ideally calls for multiple trials optimizing the l… (voir plus)earning pipeline over sources of variation such as data sampling, data augmentation, parameter initialization, and hyperparameters choices. This is prohibitively expensive, and corners are cut to reach conclusions. We model the whole benchmarking process, revealing that variance due to data sampling, parameter initialization and hyperparameter choice impact markedly the results. We analyze the predominant comparison methods used today in the light of this variance. We show a counter-intuitive result that adding more sources of variation to an imperfect estimator approaches better the ideal estimator at a 51 times reduction in compute cost. Building on these results, we study the error rate of detecting improvements, on five different deep-learning tasks/architectures. This study leads us to propose recommendations for performance comparisons.

2021-04-05

Conference on Machine Learning and Systems (Accept)