Portrait de Sarath Chandar

Sarath Chandar

Membre académique principal

sarath.chandar@mila.quebec

Chaire en IA Canada-CIFAR

Professeur associé, Polytechnique Montréal, Département d'informatique et de génie logiciel

Professeur associé, Université de Montréal, Département d'informatique et de recherche opérationnelle

Indian Institute of Technology Madras

Sujets de recherche

Alignement de l'IA

Apprentissage automatique médical

Apprentissage de représentations

Apprentissage en ligne

Apprentissage par renforcement

Apprentissage par transfert

Apprentissage profond

Apprentissage tout au long de la vie

Grands modèles de langage (LLM)

IA digne de confiance

Interprétabilité

Modèles de fondation

Optimisation

Réseaux de neurones récurrents

Systèmes multi-agents

Traitement du langage naturel

XAI (IA explicable)

Biographie

Sarath Chandar est professeur associé au départment de génie informatique et génie logiciel de Polytechnique Montréal, où il dirige le laboratoire de recherche Chandar. Il est également membre académique principal à Mila – Institut québécois d’intelligence artificielle, et titulaire d'une chaire en IA Canada-CIFAR et d'une Chaire de recherche du Canada en apprentissage machine permanent.

Ses recherches portent sur l'apprentissage tout au long de la vie, l'apprentissage profond, l'optimisation, l'apprentissage par renforcement et le traitement du langage naturel. Pour promouvoir la recherche sur l'apprentissage tout au long de la vie, Sarath Chandar a créé la Conférence sur les agents d'apprentissage tout au long de la vie (CoLLAs) en 2022 et a présidé le programme en 2022 et en 2023. Il est titulaire d'un doctorat de l'Université de Montréal et d'une maîtrise en recherche de l'Indian Institute of Technology Madras.

Étudiants actuels

Doctorat - UdeM

istabrak.abbes@mila.quebec

Maîtrise recherche - Polytechnique

alexander.aselstyne@mila.quebec

Davide Baldelli

Doctorat - Polytechnique

Co-superviseur⋅e :

davide.baldelli@mila.quebec

Collaborateur·rice de recherche

milan.bhan@mila.quebec

Diego Cerda Mardini

Maîtrise recherche - McGill

diego.cerda-mardini@mila.quebec

Prashant Govindarajan

Doctorat - Polytechnique

prashant.govindarajan@mila.quebec

Doctorat - UdeM

Superviseur⋅e principal⋅e :

guiroys@mila.quebec

Nathanaël Haas

Stagiaire de recherche - Polytechnique

nathanael.haas@mila.quebec

Maryam Hashemzadeh

Doctorat - UdeM

maryam.hashemzadeh@mila.quebec

David Heurtel--Depeiges

Doctorat - Polytechnique

david.heurtel-depeiges@mila.quebec

Doctorat - UdeM

jerry.huang@mila.quebec

Doctorat - UdeM

Co-superviseur⋅e :

kanishk.jain@mila.quebec

Postdoctorat - Polytechnique

saurav.jha@mila.quebec

Amir Ardalan Kalantari Dehaghi

Doctorat - UdeM

kalantaa@mila.quebec

Antoine Lafrance

Maîtrise recherche - Polytechnique

antoine.lafrance@mila.quebec

Doctorat - Polytechnique

lola.lebreton@mila.quebec

Postdoctorat - Polytechnique

thomas.lee@mila.quebec

Maîtrise recherche - UdeM

Co-superviseur⋅e :

aidan.li@mila.quebec

Ekaterina Lobacheva

Postdoctorat - UdeM

ekaterina.lobacheva@mila.quebec

Mansi Maheshwari

Doctorat - Polytechnique

mansi.maheshwari@mila.quebec

Roshan Munirathinam Sankaran Balaji

Collaborateur·rice de recherche - Polytechnique

roshan.munirathinam@mila.quebec

Hadi NekoeiQachkanloo

Doctorat - UdeM

nekoeihe@mila.quebec

Nilaksh Nilaksh

Doctorat - Polytechnique

nilaksh.nilaksh@mila.quebec

Doctorat - UdeM

darshan.patil@mila.quebec

Linda Peinthiere

Collaborateur·rice de recherche - Polytechnique Montreal

uphro_1@hotmail.com

Maîtrise recherche - Polytechnique

yann.pernot@mila.quebec

Mathieu Reymond

Collaborateur·rice alumni

mathieu.reymond@mila.quebec

Shaipranesh Senthilkumar

Doctorat - Polytechnique

shaipraneshgci@gmail.com

Maîtrise recherche - Polytechnique

Superviseur⋅e principal⋅e :

nour.shaheen@mila.quebec

Maîtrise recherche - UdeM

Co-superviseur⋅e :

nishant.sharma@mila.quebec

Achille Sowa Samo

Doctorat - Polytechnique

achille.sowa@mila.quebec

Postdoctorat - UdeM

Co-superviseur⋅e :

Julie Hlavacek-Larrondo

anabel.tan@mila.quebec

Maîtrise recherche - UdeM

megh.thakkar@mila.quebec

Arjun Vaithilingam Sudhakar

Doctorat - Polytechnique

arjun.vaithilingam-sudhakar@mila.quebec

Abdelrahman Zayed

Doctorat - Polytechnique

zayedabd@mila.quebec

Doctorat - Polytechnique

xutong.zhao@mila.quebec

Doctorat - Polytechnique

artem.zholus@mila.quebec

Maîtrise recherche - UdeM

Co-superviseur⋅e :

zaydzuhri@gmail.com

Billets de blogue

Improving CAD design visuals

19 décembre 2025

Optimiser la conception CAO grâce aux LLM

par

Prashant Govindarajan

Davide Baldelli

Quentin Fournier

A digital picture of Bert from Sesame street, wering black trench coat and sunglasses

3 mars 2025

NeoBERT: une nouvelle frontière pour les modèles de langage encodeurs open-source

par

Quentin Fournier

1 octobre 2024

Comment expliquer l’IA et s’assurer que cette explication est vraie? Les modèles mesurables de fidélité vous indiquent comment y parvenir

par

Siva Reddy

Publications

Memory Augmented Optimizers for Deep Learning

Paul-Aymeric McRae

Prasanna Parthasarathi

Mahmoud Assran

Popular approaches for minimizing loss in data-driven learning often involve an abstraction or an explicit retention of the history of gradi… (voir plus)ents for efficient parameter updates. The aggregated history of gradients nudges the parameter updates in the right direction even when the gradients at any given step are not informative. Although the history of gradients summarized in meta-parameters or explicitly stored in memory has been shown effective in theory and practice, the question of whether

2022-04-24

International Conference on Learning Representations (Accept (Poster))

Improving Sample Efficiency of Value Based Models Using Attention and Vision Transformers

Amir Ardalan Kalantari

Much of recent Deep Reinforcement Learning success is owed to the neural architecture's potential to learn and use effective internal repres… (voir plus)entations of the world. While many current algorithms access a simulator to train with a large amount of data, in realistic settings, including while playing games that may be played against people, collecting experience can be quite costly. In this paper, we introduce a deep reinforcement learning architecture whose purpose is to increase sample efficiency without sacrificing performance. We design this architecture by incorporating advances achieved in recent years in the field of Natural Language Processing and Computer Vision. Specifically, we propose a visually attentive model that uses transformers to learn a self-attention mechanism on the feature maps of the state representation, while simultaneously optimizing return. We demonstrate empirically that this architecture improves sample complexity for several Atari environments, while also achieving better performance in some of the games.

2022-01-31

arXiv (prépublication)

IIRC: Incremental Implicitly-Refined Classification

Mohamed Abdelsalam

Mojtaba Faramarzi

We introduce the "Incremental Implicitly-Refined Classi-fication (IIRC)" setup, an extension to the class incremental learning setup where t… (voir plus)he incoming batches of classes have two granularity levels. i.e., each sample could have a high-level (coarse) label like "bear" and a low-level (fine) label like "polar bear". Only one label is provided at a time, and the model has to figure out the other label if it has already learnfed it. This setup is more aligned with real-life scenarios, where a learner usually interacts with the same family of entities multiple times, discovers more granularity about them, while still trying not to forget previous knowledge. Moreover, this setup enables evaluating models for some important lifelong learning challenges that cannot be easily addressed under the existing setups. These challenges can be motivated by the example "if a model was trained on the class bear in one task and on polar bear in another task, will it forget the concept of bear, will it rightfully infer that a polar bear is still a bear? and will it wrongfully associate the label of polar bear to other breeds of bear?". We develop a standardized benchmark that enables evaluating models on the IIRC setup. We evaluate several state-of-the-art lifelong learning algorithms and highlight their strengths and limitations. For example, distillation-based methods perform relatively well but are prone to incorrectly predicting too many labels per image. We hope that the proposed setup, along with the benchmark, would provide a meaningful problem setting to the practitioners

2021-12-31

IEEE/CVF Conference on Computer Vision and Pattern Recognition (inconnu)

Scaling Laws for the Few-Shot Adaptation of Pre-trained Image Classifiers

Ethan Caballero

Empirical science of neural scaling laws is a rapidly growing area of significant importance to the future of machine learning, particularly… (voir plus) in the light of recent breakthroughs achieved by large-scale pre-trained models such as GPT-3, CLIP and DALL-e. Accurately predicting the neural network performance with increasing resources such as data, compute and model size provides a more comprehensive evaluation of different approaches across multiple scales, as opposed to traditional point-wise comparisons of fixed-size models on fixed-size benchmarks, and, most importantly, allows for focus on the best-scaling, and thus most promising in the future, approaches. In this work, we consider a challenging problem of few-shot learning in image classification, especially when the target data distribution in the few-shot phase is different from the source, training, data distribution, in a sense that it includes new image classes not encountered during training. Our current main goal is to investigate how the amount of pre-training data affects the few-shot generalization performance of standard image classifiers. Our key observations are that (1) such performance improvements are well-approximated by power laws (linear log-log plots) as the training set size increases, (2) this applies to both cases of target data coming from either the same or from a different domain (i.e., new classes) as the training data, and (3) few-shot performance on new classes converges at a faster rate than the standard classification performance on previously seen classes. Our findings shed new light on the relationship between scale and generalization.

2021-10-12

arXiv (prépublication)

A Survey of Data Augmentation Approaches for NLP

Steven Y. Feng

Varun Gangal

Jason Wei

Soroush Vosoughi

Teruko Mitamura

Eduard Hovy

Data augmentation has recently seen increased interest in NLP due to more work in low-resource domains, new tasks, and the popularity of lar… (voir plus)ge-scale neural networks that require large amounts of training data. Despite this recent upsurge, this area is still relatively underexplored, perhaps due to the challenges posed by the discrete nature of language data. In this paper, we present a comprehensive and unifying survey of data augmentation for NLP by summarizing the literature in a structured manner. We first introduce and motivate data augmentation for NLP, and then discuss major methodologically representative approaches. Next, we highlight techniques that are used for popular NLP applications and tasks. We conclude by outlining current challenges and directions for future research. Overall, our paper aims to clarify the landscape of existing literature in data augmentation for NLP and motivate additional work in this area. We also present a GitHub repository with a paper list that will be continuously updated at https://github.com/styfeng/DataAug4NLP

2021-07-31

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 (publié)

Continuous Coordination As a Realistic Scenario for Lifelong Learning

Akilesh Badrinaaraayanan

Aaron Courville

Current deep reinforcement learning (RL) algorithms are still highly task-specific and lack the ability to generalize to new environments. L… (voir plus)ifelong learning (LLL), however, aims at solving multiple tasks sequentially by efficiently transferring and using knowledge between tasks. Despite a surge of interest in lifelong RL in recent years, the lack of a realistic testbed makes robust evaluation of LLL algorithms difficult. Multi-agent RL (MARL), on the other hand, can be seen as a natural scenario for lifelong RL due to its inherent non-stationarity, since the agents' policies change over time. In this work, we introduce a multi-agent lifelong learning testbed that supports both zero-shot and few-shot settings. Our setup is based on Hanabi -- a partially-observable, fully cooperative multi-agent game that has been shown to be challenging for zero-shot coordination. Its large strategy space makes it a desirable environment for lifelong RL tasks. We evaluate several recent MARL methods, and benchmark state-of-the-art LLL algorithms in limited memory and computation regimes to shed light on their strengths and weaknesses. This continual learning paradigm also provides us with a pragmatic way of going beyond centralized training which is the most commonly used training protocol in MARL. We empirically show that the agents trained in our setup are able to coordinate well with unseen agents, without any additional assumptions made by previous works. The code and all pre-trained models are available at https://github.com/chandar-lab/Lifelong-Hanabi.

2021-07-19

International Conference on Machine Learning (Spotlight)

proceedings.mlr.press

A Brief Study on the Effects of Training Generative Dialogue Models with a Semantic loss

Prasanna Parthasarathi

Mohamed Abdelsalam

Neural models trained for next utterance generation in dialogue task learn to mimic the n-gram sequences in the training set with training o… (voir plus)bjectives like negative log-likelihood (NLL) or cross-entropy. Such commonly used training objectives do not foster generating alternate responses to a context. But, the effects of minimizing an alternate training objective that fosters a model to generate alternate response and score it on semantic similarity has not been well studied. We hypothesize that a language generation model can improve on its diversity by learning to generate alternate text during training and minimizing a semantic loss as an auxiliary objective. We explore this idea on two different sized data sets on the task of next utterance generation in goal oriented dialogues. We make two observations (1) minimizing a semantic objective improved diversity in responses in the smaller data set (Frames) but only as-good-as minimizing the NLL in the larger data set (MultiWoZ) (2) large language model embeddings can be more useful as a semantic loss objective than as initialization for token embeddings.

2021-06-30

Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue (publié)

Towered Actor Critic For Handling Multiple Action Types In Reinforcement Learning For Drug Discovery

Sai Krishna Gottipati

Yashaswi Pathak

Boris Sattarov

Sahir

Rohan Nuttall

Matthew E. Taylor

Reinforcement learning (RL) has made significant progress in both abstract and real-world domains, but the majority of state-of-the-art algo… (voir plus)rithms deal only with monotonic actions. However, some applications require agents to reason over different types of actions. Our application simulates reaction-based molecule generation, used as part of the drug discovery pipeline, and includes both uni-molecular and bi-molecular reactions. This paper introduces a novel framework, towered actor critic (TAC), to handle multiple action types. The TAC framework is general in that it is designed to be combined with any existing RL algorithms for continuous action space. We combine it with TD3 to empirically obtain significantly better results than existing methods in the drug discovery setting. TAC is also applied to RL benchmarks in OpenAI Gym and results show that our framework can improve, or at least does not hurt, performance relative to standard TD3.

2021-05-17

AAAI Conference on Artificial Intelligence (publié)

Learning to Navigate the Synthetically Accessible Chemical Space Using Reinforcement Learning

Sai Krishna Gottipati

Boris Sattarov

Sufeng Niu

Yashaswi Pathak

Haoran Wei

Karam J. Thomas

Simon Blackburn

Connor W. Coley

Over the last decade, there has been significant progress in the field of machine learning for de novo drug design, particularly in deep gen… (voir plus)erative models. However, current generative approaches exhibit a significant challenge as they do not ensure that the proposed molecular structures can be feasibly synthesized nor do they provide the synthesis routes of the proposed small molecules, thereby seriously limiting their practical applicability. In this work, we propose a novel forward synthesis framework powered by reinforcement learning (RL) for de novo drug design, Policy Gradient for Forward Synthesis (PGFS), that addresses this challenge by embedding the concept of synthetic accessibility directly into the de novo drug design system. In this setup, the agent learns to navigate through the immense synthetically accessible chemical space by subjecting commercially available small molecule building blocks to valid chemical reactions at every time step of the iterative virtual multi-step synthesis process. The proposed environment for drug discovery provides a highly challenging test-bed for RL algorithms owing to the large state space and high-dimensional continuous action space with hierarchical actions. PGFS achieves state-of-the-art performance in generating structures with high QED and penalized clogP. Moreover, we validate PGFS in an in-silico proof-of-concept associated with three HIV targets. Finally, we describe how the end-to-end training conceptualized in this study represents an important paradigm in radically expanding the synthesizable chemical space and automating the drug discovery process.

2020-07-13

International Conference on Machine Learning (Accept)

proceedings.mlr.press

A Reinforcement Learning Pipeline for Band Gap-directed Crystal Generation

Prashant Govindarajan

Mathieu Reymond

Santiago Miret

Antoine Clavaud

Mariano Phielipp

Property-driven AI-automated material discovery presents unique challenges owing to the complex nature of the chemical structural space and … (voir plus)computationally expensive simulations. For crystalline solids, the band gap is an important property for designing semiconductors and batteries. However, optimizing crystals for a target band gap is difficult and not well-explored. Reinforcement learning (RL) shows promise towards optimizing crystals, as it can freely explore the chemical space. However, it relies on regular band gap evaluations, which can only be accurately computed through expensive Density Functional Theory (DFT) simulations. In this study, we propose an active learning-inspired pipeline that combines RL and DFT simulations for optimizing crystal compositions given a target band gap. The pipeline includes an RL policy for predicting atom types and a band gap network that is fine-tuned with DFT data. Preliminary results indicate the need for furthering the state-of-the-art to address the inherent challenges of the problem.

2019-12-31

International Conference on Machine Learning (publié)

Toward Training Recurrent Neural Networks for Lifelong Learning.

Catastrophic forgetting and capacity saturation are the central challenges of any parametric lifelong learning system. In this work, we stud… (voir plus)y these challenges in the context of sequential supervised learning with an emphasis on recurrent neural networks. To evaluate the models in the lifelong learning setting, we propose a curriculum-based, simple, and intuitive benchmark where the models are trained on tasks with increasing levels of difficulty. To measure the impact of catastrophic forgetting, the model is tested on all the previous tasks as it completes any task. As a step toward developing true lifelong learning systems, we unify gradient episodic memory (a catastrophic forgetting alleviation approach) and Net2Net (a capacity expansion approach). Both models are proposed in the context of feedforward networks, and we evaluate the feasibility of using them for recurrent networks. Evaluation on the proposed benchmark shows that the unified model is more suitable than the constituent models for lifelong learning setting.

2019-12-31

Neural Computation (publié)

Towards Non-Saturating Recurrent Units for Modelling Long-Term Dependencies

Chinnadhurai Sankar

Eugene Vorontsov

Samira Ebrahimi Kahou

Modelling long-term dependencies is a challenge for recurrent neural networks. This is primarily due to the fact that gradients vanish durin… (voir plus)g training, as the sequence length increases. Gradients can be attenuated by transition operators and are attenuated or dropped by activation functions. Canonical architectures like LSTM alleviate this issue by skipping information through a memory mechanism. We propose a new recurrent architecture (Non-saturating Recurrent Unit; NRU) that relies on a memory mechanism but forgoes both saturating activation functions and saturating gates, in order to further alleviate vanishing gradients. In a series of synthetic and real world tasks, we demonstrate that the proposed model is the only model that performs among the top 2 models across all tasks with and without long-term dependencies, when compared against a range of other architectures.

2019-07-16

AAAI Conference on Artificial Intelligence (publié)