Doina Precup

Sumana Basu

Collaborating Alumni - McGill University

Co-supervisor :

Adriana Romero Soriano

Collaborating Alumni - McGill University

Lynn Cherif

Collaborating Alumni - McGill University

Co-supervisor :

PhD - McGill University

Co-supervisor :

PhD - McGill University

Principal supervisor :

David Meger

Jonathan Colaço Carr

Master's Research - McGill University

Principal supervisor :

Prakash Panangaden

Élodie Coté-Gauthier

Collaborating researcher - McGill University

Co-supervisor :

Isabeau Prémont-Schwarz

Franco Del Balso

Collaborating researcher - Université de Montréal

Jesse Farebrother

PhD - McGill University

Principal supervisor :

Marc Gendron-Bellemare

PhD - McGill University

Principal supervisor :

Collaborating researcher - Birla Institute of Technology

Howard Huang

PhD - McGill University

Haque Ishfaq

Collaborating Alumni - McGill University

Mohammad Sami Nur Islam Islam

Master's Research - McGill University

Arushi Jain

Collaborating Alumni - McGill University

PhD - Polytechnique Montréal

Martin Klissarov

PhD - McGill University

Postdoctorate - McGill University

Jonathan Lebensold

Collaborating Alumni - McGill University

Collaborating Alumni - McGill University

Ray Luo

PhD - McGill University

Principal supervisor :

G McCracken

PhD - McGill University

Nazanin Mohammadi Sepahvand

Collaborating Alumni - McGill University

Shahrad Mohammadzadeh

Master's Research - McGill University

Principal supervisor :

Gabriela Moisescu-Pareja

Collaborating researcher - McGill University

Co-supervisor :

Irina Rish

Padideh Nouri

PhD - Université de Montréal

Co-supervisor :

PhD - McGill University

Co-supervisor :

Nate Rahn

PhD - McGill University

Principal supervisor :

Marc Gendron-Bellemare

Sahand Rezaei-Shoshtari

PhD - McGill University

Co-supervisor :

PhD - McGill University

Co-supervisor :

PhD - McGill University

Co-supervisor :

PhD - McGill University

Nishanth Anand Vemgal

PhD - McGill University

PhD - McGill University

Co-supervisor :

Samira Ebrahimi Kahou

Zihan Wang

PhD - McGill University

Skipper: Combining Spatial and Temporal Abstraction for Better Generalization

Guangyuan Wang

Research Intern - McGill University

Steve Wen

Master's Research - McGill University

Co-supervisor :

Gregory Dudek

Zijing Wu

PhD - McGill University

Principal supervisor :

PhD - McGill University

Harry Zhao

Collaborating Alumni - McGill University

Co-supervisor :

Blog Posts

Generic thumbnail for Mila Blog articles.

February 22, 2024

Mingde Harry Zhao

Safa Alver

Harm van Seijen

Romain Laroche

Doina Precup

Yoshua Bengio

Read the article

Publications

RL Fine-Tuning Heals OOD Forgetting in SFT

Sicheng Lyu

Mohammad Hamdaqa

The two-stage fine-tuning paradigm of Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has empirically shown better reas… (see more)oning performance than one-stage SFT for the post-training of Large Language Models (LLMs). However, the evolution and mechanism behind the synergy of SFT and RL are still under-explored and inconclusive. In our study, we find the well-known claim "SFT memorizes, RL generalizes" is over-simplified, and discover that: (1) OOD performance peaks at the early stage of SFT and then declines (OOD forgetting), the best SFT checkpoint cannot be captured by training/test loss; (2) the subsequent RL stage does not generate fundamentally better OOD capability, instead it plays an \textbf{OOD restoration} role, recovering the lost reasoning ability during SFT; (3) The recovery ability has boundaries, \ie{} \textbf{if SFT trains for too short or too long, RL cannot recover the lost OOD ability;} (4) To uncover the underlying mechanisms behind the forgetting and restoration process, we employ SVD analysis on parameter matrices, manually edit them, and observe their impacts on model performance. Unlike the common belief that the shift of model capacity mainly results from the changes of singular values, we find that they are actually quite stable throughout fine-tuning. Instead, the OOD behavior strongly correlates with the \textbf{rotation of singular vectors}. Our findings re-identify the roles of SFT and RL in the two-stage fine-tuning and discover the rotation of singular vectors as the key mechanism. %reversing the rotations induced by SFT, which shows recovery from forgetting, whereas imposing the SFT parameter directions onto a RL-tuned model results in performance degradation. Code is available at https://github.com/xiaodanguoguo/RL_Heals_SFT

2024-12-31

arXiv (preprint)

Incorporating Spatial Information into Goal-Conditioned Hierarchical Reinforcement Learning via Graph Representations

Shuyuan Zhang

Zihan Wang

Xiao-Wen Chang

The integration of graphs with Goal-conditioned Hierarchical Reinforcement Learning (GCHRL) has recently gained attention, as intermediate g… (see more)oals (subgoals) can be effectively sampled from graphs that naturally represent the overall task structure in most RL tasks. However, existing approaches typically rely on domain-specific knowledge to construct these graphs, limiting their applicability to new tasks. Other graph-based approaches create graphs dynamically during exploration but struggle to fully utilize them, because they have problems passing the information in the graphs to newly visited states. Additionally, current GCHRL methods face challenges such as sample inefficiency and poor subgoal representation. This paper proposes a solution to these issues by developing a graph encoder-decoder to evaluate unseen states. Our proposed method, Graph-Guided sub-Goal representation Generation RL (G4RL), can be incorporated into any existing GCHRL method when operating in environments with primarily symmetric and reversible transitions to enhance performance across this class of problems. We show that the graph encoder-decoder can be effectively implemented using a network trained on the state graph generated during exploration. Empirical results indicate that leveraging high and low-level intrinsic rewards from the graph encoder-decoder significantly enhances the performance of state-of-the-art GCHRL approaches with an extra small computational cost in dense and sparse reward environments.

2024-12-31

Trans. Mach. Learn. Res. (published)

Training Language Models to Self-Correct via Reinforcement Learning

Aviral Kumar

Vincent Zhuang

Rishabh Agarwal

Yi Su

John D Co-Reyes

Avi Singh

Kate Baumli

Shariq Iqbal

Colton Bishop

Rebecca Roelofs

Lei M Zhang

Kay McKinney

Disha Shrivastava

Cosmin Paduraru

George Tucker

Feryal Behbahani

Aleksandra Faust

Self-correction is a highly desirable capability of large language models (LLMs), yet it has consistently been found to be largely ineffecti… (see more)ve in modern LLMs. Existing approaches for training self-correction either require multiple models or rely on a more capable model or other forms of supervision. To this end, we develop a multi-turn online reinforcement learning (RL) approach, SCoRe, that significantly improves an LLM's self-correction ability using entirely self-generated data. To build SCoRe, we first show that variants of supervised fine-tuning (SFT) on offline model-generated correction traces are insufficient for instilling self-correction behavior. In particular, we observe that training via SFT either suffers from a distribution mismatch between the training data and the model's own responses or implicitly prefers only a certain mode of correction behavior that is often not effective at test time. SCoRe addresses these challenges by training under the model's own distribution of self-generated correction traces and using appropriate regularization to steer the learning process into learning a self-correction strategy that is effective at test time as opposed to simply fitting high-reward responses for a given prompt. This regularization prescribes running a first phase of RL on a base model to generate a policy initialization that is less susceptible to collapse and then using a reward bonus to amplify self-correction during training. When applied to Gemini 1.0 Pro and 1.5 Flash models, we find that SCoRe achieves state-of-the-art self-correction performance, improving the base models' self-correction by 15.6% and 9.1% respectively on the MATH and HumanEval benchmarks.

2024-12-31

ICLR (published)

Fairness in Reinforcement Learning with Bisimulation Metrics

Sahand Rezaei-Shoshtari

Ensuring long-term fairness is crucial when developing automated decision making systems, specifically in dynamic and sequential environment… (see more)s. By maximizing their reward without consideration of fairness, AI agents can introduce disparities in their treatment of groups or individuals. In this paper, we establish the connection between bisimulation metrics and group fairness in reinforcement learning. We propose a novel approach that leverages bisimulation metrics to learn reward functions and observation dynamics, ensuring that learners treat groups fairly while reflecting the original problem. We demonstrate the effectiveness of our method in addressing disparities in sequential decision making problems through empirical evaluation on a standard fairness benchmark consisting of lending and college admission scenarios.

2024-12-21

ArXiv (preprint)

Towards AI-designed genomes using a variational autoencoder

Natasha K. Dudek

Genomes encode elaborate networks of genes whose products must seamlessly interact to support living organisms. Humans’ capacity to unders… (see more)tand these biological systems is limited by their sheer size and complexity. In this article, we develop a proof of concept framework for training a machine learning (ML) algorithm to model bacterial genome composition. To achieve this, we create simplified representations of genomes in the form of binary vectors that indicate the encoded genes, henceforth referred to as genome vectors. A denoising variational autoencoder was trained to accept corrupted genome vectors, in which most genes had been masked, and reconstruct the original. The resulting model, DeepGenomeVector, effectively captures complex dependencies in genomic networks, as evaluated by both qualitative and quantitative metrics. An in-depth functional analysis of a generated genome vector shows that its encoded pathways are interconnected, near complete, and ecologically cohesive. On the test set, where the model’s ability to reconstruct uncorrupted genome vectors was evaluated, Area Under the Receiver Operating Curve (AUROC) and F1 scores of 0.98 and 0.83, respectively, support the model’s strong performance. This article showcases the power of ML approaches for synthetic biology and highlights the possibility that artifical intelligence agents may one day be able to design genomes that animate carbon-based cells.

2024-11-30

Proceedings of the Royal Society B: Biological Sciences (published)

Reaction-conditioned De Novo Enzyme Design with GENzyme

Chenqing Hua

Jiarui Lu

Yang Liu

Odin Zhang

Jian Tang

Rex Ying

Wengong Jin

Guy Wolf

Shuangjia Zheng

The introduction of models like RFDiffusionAA, AlphaFold3, AlphaProteo, and Chai1 has revolutionized protein structure modeling and interact… (see more)ion prediction, primarily from a binding perspective, focusing on creating ideal lock-and-key models. However, these methods can fall short for enzyme-substrate interactions, where perfect binding models are rare, and induced fit states are more common. To address this, we shift to a functional perspective for enzyme design, where the enzyme function is defined by the reaction it catalyzes. Here, we introduce \textsc{GENzyme}, a \textit{de novo} enzyme design model that takes a catalytic reaction as input and generates the catalytic pocket, full enzyme structure, and enzyme-substrate binding complex. \textsc{GENzyme} is an end-to-end, three-staged model that integrates (1) a catalytic pocket generation and sequence co-design module, (2) a pocket inpainting and enzyme inverse folding module, and (3) a binding and screening module to optimize and predict enzyme-substrate complexes. The entire design process is driven by the catalytic reaction being targeted. This reaction-first approach allows for more accurate and biologically relevant enzyme design, potentially surpassing structure-based and binding-focused models in creating enzymes capable of catalyzing specific reactions. We provide \textsc{GENzyme} code at https://github.com/WillHua127/GENzyme.

2024-11-09

ArXiv (preprint)

Soft Condorcet Optimization for Ranking of General Agents

Marc Lanctot

Kate Larson

Michael Kaisers

Quentin Berthet

Ian Gemp

Manfred Diaz

Roberto-Rafael Maura-Rivero

Yoram Bachrach

Anna Koop

A common way to drive progress of AI models and agents is to compare their performance on standardized benchmarks. Comparing the performance… (see more) of general agents requires aggregating their individual performances across a potentially wide variety of different tasks. In this paper, we describe a novel ranking scheme inspired by social choice frameworks, called Soft Condorcet Optimization (SCO), to compute the optimal ranking of agents: the one that makes the fewest mistakes in predicting the agent comparisons in the evaluation data. This optimal ranking is the maximum likelihood estimate when evaluation data (which we view as votes) are interpreted as noisy samples from a ground truth ranking, a solution to Condorcet's original voting system criteria. SCO ratings are maximal for Condorcet winners when they exist, which we show is not necessarily true for the classical rating system Elo. We propose three optimization algorithms to compute SCO ratings and evaluate their empirical performance. When serving as an approximation to the Kemeny-Young voting method, SCO rankings are on average 0 to 0.043 away from the optimal ranking in normalized Kendall-tau distance across 865 preference profiles from the PrefLib open ranking archive. In a simulated noisy tournament setting, SCO achieves accurate approximations to the ground truth ranking and the best among several baselines when 59\% or more of the preference data is missing. Finally, SCO ranking provides the best approximation to the optimal ranking, measured on held-out test sets, in a problem containing 52,958 human players across 31,049 games of the classic seven-player game of Diplomacy.

2024-10-31

arXiv (published)

Effective Protein-Protein Interaction Exploration with PPIretrieval

Chenqing Hua

Connor W. Coley

Guy Wolf

Shuangjia Zheng

2024-10-12

NeurIPS.cc/2024/Workshop/AIDrugX (poster)

EnzymeFlow: Generating Reaction-specific Enzyme Catalytic Pockets through Flow Matching and Co-Evolutionary Dynamics

Yang Liu

Odin Zhang

Kevin K Yang

Shuangjia Zheng

2024-10-12

NeurIPS.cc/2024/Workshop/AIDrugX (poster)

Rejecting Hallucinated State Targets during Planning

Mingde “Harry” Zhao

Tristan Sylvain

Romain Laroche

Yoshua Bengio

In planning processes of computational decision-making agents, generative or predictive models are often used as "generators" to propose "ta… (see more)rgets" representing sets of expected or desirable states. Unfortunately, learned models inevitably hallucinate infeasible targets that can cause delusional behaviors and safety concerns. We first investigate the kinds of infeasible targets that generators can hallucinate. Then, we devise a strategy to identify and reject infeasible targets by learning a target feasibility evaluator. To ensure that the evaluator is robust and non-delusional, we adopted a design choice combining off-policy compatible learning rule, distributional architecture, and data augmentation based on hindsight relabeling. Attaching to a planning agent, the designed evaluator learns by observing the agent's interactions with the environment and the targets produced by its generator, without the need to change the agent or its generator. Our controlled experiments show significant reductions in delusional behaviors and performance improvements for various kinds of existing agents.

2024-10-11

NeurIPS.cc/2024/Workshop/SafeGenAi (poster)

proceedings.mlr.press

Mitigating Downstream Model Risks via Model Provenance

Keyu Wang

Abdullah Norozi Iranzad

Scott Schaffter

Jonathan Lebensold

Meg Risdal

Research and industry are rapidly advancing the innovation and adoption of foundation model-based systems, yet the tools for managing these … (see more)models have not kept pace. Understanding the provenance and lineage of models is critical for researchers, industry, regulators, and public trust. While model cards and system cards were designed to provide transparency, they fall short in key areas: tracing model genealogy, enabling machine readability, offering reliable centralized management systems, and fostering consistent creation incentives. This challenge mirrors issues in software supply chain security, but AI/ML remains at an earlier stage of maturity. Addressing these gaps requires industry-standard tooling that can be adopted by foundation model publishers, open-source model innovators, and major distribution platforms. We propose a machine-readable model specification format to simplify the creation of model records, thereby reducing error-prone human effort, notably when a new model inherits most of its design from a foundation model. Our solution explicitly traces relationships between upstream and downstream models, enhancing transparency and traceability across the model lifecycle. To facilitate the adoption, we introduce the unified model record (UMR) repository , a semantically versioned system that automates the publication of model records to multiple formats (PDF, HTML, LaTeX) and provides a hosted web interface (https://modelrecord.com/). This proof of concept aims to set a new standard for managing foundation models, bridging the gap between innovation and responsible model management.

2024-10-08

NeurIPS.cc/2024/Workshop/SoLaR (poster)

ReactZyme: A Benchmark for Enzyme-Reaction Prediction

Bozitao Zhong

Liang Hong

Shuangjia Zheng

Enzymes, with their specific catalyzed reactions, are necessary for all aspects of life, enabling diverse biological processes and adaptatio… (see more)ns. Predicting enzyme functions is essential for understanding biological pathways, guiding drug development, enhancing bioproduct yields, and facilitating evolutionary studies. Addressing the inherent complexities, we introduce a new approach to annotating enzymes based on their catalyzed reactions. This method provides detailed insights into specific reactions and is adaptable to newly discovered reactions, diverging from traditional classifications by protein family or expert-derived reaction classes. We employ machine learning algorithms to analyze enzyme reaction datasets, delivering a much more refined view on the functionality of enzymes. Our evaluation leverages the largest enzyme-reaction dataset to date, derived from the SwissProt and Rhea databases with entries up to January 8, 2024. We frame the enzyme-reaction prediction as a retrieval problem, aiming to rank enzymes by their catalytic ability for specific reactions. With our model, we can recruit proteins for novel reactions and predict reactions in novel proteins, facilitating enzyme discovery and function annotation (https://github.com/WillHua127/ReactZyme).

2024-09-25

NeurIPS.cc/2024/Datasets_and_Benchmarks_Track (poster)