Alex Hernández-García

Membre académique principal

alex.hernandez-garcia@mila.quebec

Professeur adjoint, Université de Montréal

Sujets de recherche

Apprentissage actif

Apprentissage de représentations

Apprentissage profond

Biologie computationnelle

Climat

Découverte de médicaments

GFlowNets

IA et durabilité

IA pour la science

Modèles génératifs

Modèles probabilistes

Modélisation moléculaire

Optimisation en boîte noire

Réduction d'échelle des variables climatiques

Site web

Google Scholar

Biographie

Alex Hernandez-Garcia est professeur adjoint à l’Université de Montréal, membre académique principal de Mila, professeur IVADO et membre de l’Institut Courtois. Ses recherches en apprentissage automatique sont motivées par des applications scientifiques visant à relever la crise climatique et d’autres défis sociétaux. Un axe actuel de ses travaux porte en particulier sur l’apprentissage automatique actif et génératif afin de faciliter les découvertes scientifiques, telles que de nouveaux matériaux et antibiotiques. Il plaide également pour un examen critique des impacts de l’intelligence artificielle, est un fervent défenseur de la science ouverte et participe activement à des initiatives visant à rendre la science plus inclusive, équitable, ouverte, reproductible, transparente et respectueuse de l’environnement.

Étudiants actuels

Sanad Abu Baker

Stagiaire de recherche - UdeM

sanad.abubaker@mila.quebec

Tim Arni

Stagiaire de recherche - UdeM

tim.arni@mila.quebec

Github

Dionessa Biton

Maîtrise recherche - UdeM

dionessa.biton@mila.quebec

Github

Google Scholar

Minkyu Kim

Visiteur de recherche indépendant - KAIST

minkyu.kim@mila.quebec

Site web

Github

Google Scholar

Hyeonah Kim

Postdoctorat - UdeM

Co-superviseur⋅e :

Yoshua Bengio

hyeonah.kim@mila.quebec

Ethan Kreuzer

Maîtrise recherche - UdeM

Superviseur⋅e principal⋅e :

Dominique Beaini

ethan.kreuzer@mila.quebec

Pierre-Louis Lemaire

Collaborateur·rice de recherche - Polytechnique Montréal

Co-superviseur⋅e :

David Rolnick

pierre-louis.lemaire@mila.quebec

Site web

Ameer Nizami

Doctorat - Concordia

ameer.nizami@mila.quebec

Github

Google Scholar

Ola Onabola

Doctorat - UdeM

walexi4great@gmail.com

Maîtrise recherche - UdeM

celine.roget@mila.quebec

Github

Dounia Shaaban Kabakibo

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Michel Côté

dounia.shaaban-kabakibo@mila.quebec

Github

Google Scholar

Divya Sharma

Postdoctorat - UdeM

Superviseur⋅e principal⋅e :

Yoshua Bengio

divya.sharma@mila.quebec

Site web

Github

Publications

Learning Decision Trees as Amortized Structure Inference

Mohammed Mahfoud

Ghait Boukachab

Michał Koziarski

Alex Hernández-García

Stefan Bauer

Yoshua Bengio

Nikolay Malkin

2025-03-04

ICLR.cc/2025/Workshop/FPI (poster)

doi.org

openreview.net

Multi-Fidelity Active Learning with GFlowNets

Alex Hernández-García

Nikita Saxena

Moksh J. Jain

Cheng-Hao Liu

Yoshua Bengio

In the last decades, the capacity to generate large amounts of data in science and engineering applications has been growing steadily. Meanw… (voir plus)hile, the progress in machine learning has turned it into a suitable tool to process and utilise the available data. Nonetheless, many relevant scientific and engineering problems present challenges where current machine learning methods cannot yet efficiently leverage the available data and resources. For example, in scientific discovery, we are often faced with the problem of exploring very large, high-dimensional spaces, where querying a high fidelity, black-box objective function is very expensive. Progress in machine learning methods that can efficiently tackle such problems would help accelerate currently crucial areas such as drug and materials discovery. In this paper, we propose the use of GFlowNets for multi-fidelity active learning, where multiple approximations of the black-box function are available at lower fidelity and cost. GFlowNets are recently proposed methods for amortised probabilistic inference that have proven efficient for exploring large, high-dimensional spaces and can hence be practical in the multi-fidelity setting too. Here, we describe our algorithm for multi-fidelity active learning with GFlowNets and evaluate its performance in both well-studied synthetic tasks and practically relevant applications of molecular discovery. Our results show that multi-fidelity active learning with GFlowNets can efficiently leverage the availability of multiple oracles with different costs and fidelities to accelerate scientific discovery and engineering design.

2024-07-24

TMLR (accepté)

doi.org

openreview.net

PhAST: Physics-Aware, Scalable, and Task-Specific GNNs for Accelerated Catalyst Design

Alexandre Duval

Victor Schmidt

Santiago Miret

Yoshua Bengio

Alex Hernández-García

David Rolnick

Mitigating the climate crisis requires a rapid transition towards lower-carbon energy. Catalyst materials play a crucial role in the electro… (voir plus)chemical reactions involved in numerous industrial processes key to this transition, such as renewable energy storage and electrofuel synthesis. To reduce the energy spent on such activities, we must quickly discover more efficient catalysts to drive electrochemical reactions. Machine learning (ML) holds the potential to efficiently model materials properties from large amounts of data, accelerating electrocatalyst design. The Open Catalyst Project OC20 dataset was constructed to that end. However, ML models trained on OC20 are still neither scalable nor accurate enough for practical applications. In this paper, we propose task-specific innovations applicable to most architectures, enhancing both computational efficiency and accuracy. This includes improvements in (1) the graph creation step, (2) atom representations, (3) the energy prediction head, and (4) the force prediction head. We describe these contributions, referred to as PhAST, and evaluate them thoroughly on multiple architectures. Overall, PhAST improves energy MAE by 4 to 42

2024-07-22

International Conference on Machine Learning (Accept (Poster))

doi.org

openreview.net

Multi-variable Hard Physical Constraints for Climate Model Downscaling

Jose González-Abad

Alex Hernández-García

Paula Harder

David Rolnick

José Manuel Gutiérrez

Global Climate Models (GCMs) are the primary tool to simulate climate evolution and assess the impacts of climate change. However, they ofte… (voir plus)n operate at a coarse spatial resolution that limits their accuracy in reproducing local-scale phenomena. Statistical downscaling methods leveraging deep learning offer a solution to this problem by approximating local-scale climate fields from coarse variables, thus enabling regional GCM projections. Typically, climate fields of different variables of interest are downscaled independently, resulting in violations of fundamental physical properties across interconnected variables. This study investigates the scope of this problem and, through an application on temperature, lays the foundation for a framework introducing multi-variable hard constraints that guarantees physical relationships between groups of downscaled climate variables.

2024-01-21

AAAI Symposium Series (publié)

doi.org

arxiv.org

Fourier Neural Operators for Arbitrary Resolution Climate Data Downscaling

Qidong Yang

Alex Hernández-García

Paula Harder

Venkatesh Ramesh

Prasanna Sattegeri

Daniela Szwarcman

Campbell D. Watson

David Rolnick

Climate simulations are essential in guiding our understanding of climate change and responding to its effects. However, it is computational… (voir plus)ly expensive to resolve complex climate processes at high spatial resolution. As one way to speed up climate simulations, neural networks have been used to downscale climate variables from fast-running low-resolution simulations, but high-resolution training data are often unobtainable or scarce, greatly limiting accuracy. In this work, we propose a downscaling method based on the Fourier neural operator. It trains with data of a small upsampling factor and then can zero-shot downscale its input to arbitrary unseen high resolution. Evaluated both on ERA5 climate model data and on the Navier-Stokes equation solution data, our downscaling model significantly outperforms state-of-the-art convolutional and generative adversarial downscaling models, both in standard single-resolution downscaling and in zero-shot generalization to higher upsampling factors. Furthermore, we show that our method also outperforms state-of-the-art data-driven partial differential equation solvers on Navier-Stokes equations. Overall, our work bridges the gap between simulation of a physical process and interpolation of low-resolution output, showing that it is possible to combine both approaches and significantly improve upon each other.

2023-12-31

Journal of Machine Learning Research (publié)

doi.org

arxiv.org

Towards equilibrium molecular conformation generation with GFlowNets

Alexandra Volokhova

Michał Koziarski

Alex Hernández-García

Cheng-Hao Liu

Santiago Miret

Pablo Lemos

Luca Thiede

Zichao Yan

Alán Aspuru-Guzik

Yoshua Bengio

Sampling diverse, thermodynamically feasible molecular conformations plays a crucial role in predicting properties of a molecule. In this pa… (voir plus)per we propose to use GFlowNet for sampling conformations of small molecules from the Boltzmann distribution, as determined by the molecule's energy. The proposed approach can be used in combination with energy estimation methods of different fidelity and discovers a diverse set of low-energy conformations for highly flexible drug-like molecules. We demonstrate that GFlowNet can reproduce molecular potential energy surfaces by sampling proportionally to the Boltzmann distribution.

2023-12-31

Digital Discovery (publié)

doi.org

openreview.net

Crystal-GFN: sampling materials with desirable properties and constraints

Mistal

Alex Hernández-García

Alexandra Volokhova

Alexandre AGM Duval

2023-10-26

NeurIPS.cc/2023/Workshop/AI4Mat (spotlight)

openreview.net

On the importance of catalyst-adsorbate 3D interactions for relaxed energy predictions

Alvaro Carbonero

Alexandre Duval

Victor Schmidt

Santiago Miret

Alex Hernández-García

Yoshua Bengio

David Rolnick

The use of machine learning for material property prediction and discovery has traditionally centered on graph neural networks that incorpor… (voir plus)ate the geometric configuration of all atoms. However, in practice not all this information may be readily available, e.g.~when evaluating the potentially unknown binding of adsorbates to catalyst. In this paper, we investigate whether it is possible to predict a system's relaxed energy in the OC20 dataset while ignoring the relative position of the adsorbate with respect to the electro-catalyst. We consider SchNet, DimeNet++ and FAENet as base architectures and measure the impact of four modifications on model performance: removing edges in the input graph, pooling independent representations, not sharing the backbone weights and using an attention mechanism to propagate non-geometric relative information. We find that while removing binding site information impairs accuracy as expected, modified models are able to predict relaxed energies with remarkably decent MAE. Our work suggests future research directions in accelerated materials discovery where information on reactant configurations can be reduced or altogether omitted.

2023-10-26

NeurIPS.cc/2023/Workshop/AI4Mat (poster)

doi.org

openreview.net

Crystal-GFN: sampling crystals with desirable properties and constraints

Mila AI4Science

Alex Hernández-García

Alexandra Volokhova

Yasmine Benabed

Gian-Marco Rignanese

Pierre-Paul De Breuck

Paulette Clancy

Accelerating material discovery holds the potential to greatly help mitigate the climate crisis. Discovering new solid-state materials such … (voir plus)as electrocatalysts, super-ionic conductors or photovoltaic materials can have a crucial impact, for instance, in improving the efficiency of renewable energy production and storage. In this paper, we introduce Crystal-GFN, a generative model of crystal structures that sequentially samples structural properties of crystalline materials, namely the space group, composition and lattice parameters. This domain-inspired approach enables the flexible incorporation of physical and structural hard constraints, as well as the use of any available predictive model of a desired physicochemical property as an objective function. To design stable materials, one must target the candidates with the lowest formation energy. Here, we use as objective the formation energy per atom of a crystal structure predicted by a new proxy machine learning model trained on MatBench. The results demonstrate that Crystal-GFN is able to sample highly diverse crystals with low (median -3.1 eV/atom) predicted formation energy.

2023-10-06

arXiv (prépublication)

doi.org

arxiv.org

Multi-variable Hard Physical Constraints for Climate Model Downscaling

Jose Gonz'alez-Abad

'Alex Hern'andez-Garc'ia

Paula Harder

David Rolnick

Jos'e Manuel Guti'errez

2023-08-01

ArXiv (prépublication)

doi.org

arxiv.org

Multi-Objective GFlowNets

Moksh Jain

Sharath Chandra Raparthy

Alex Hernández-García

Jarrid Rector-Brooks

Yoshua Bengio

Santiago Miret

Emmanuel Bengio

We study the problem of generating diverse candidates in the context of Multi-Objective Optimization. In many applications of machine learni… (voir plus)ng such as drug discovery and material design, the goal is to generate candidates which simultaneously optimize a set of potentially conflicting objectives. Moreover, these objectives are often imperfect evaluations of some underlying property of interest, making it important to generate diverse candidates to have multiple options for expensive downstream evaluations. We propose Multi-Objective GFlowNets (MOGFNs), a novel method for generating diverse Pareto optimal solutions, based on GFlowNets. We introduce two variants of MOGFNs: MOGFN-PC, which models a family of independent sub-problems defined by a scalarization function, with reward-conditional GFlowNets, and MOGFN-AL, which solves a sequence of sub-problems defined by an acquisition function in an active learning loop. Our experiments on wide variety of synthetic and benchmark tasks demonstrate advantages of the proposed methods in terms of the Pareto performance and importantly, improved candidate diversity, which is the main contribution of this work.

2023-07-24

ICML (Accept (Poster))

doi.org

proceedings.mlr.press

A Theory of Continuous Generative Flow Networks

Alexandra Volokhova

Alex Hernández-García

Lena Nehale Ezzine

Yoshua Bengio

Nikolay Malkin

Generative flow networks (GFlowNets) are amortized variational inference algorithms that are trained to sample from unnormalized target dist… (voir plus)ributions over compositional objects. A key limitation of GFlowNets until this time has been that they are restricted to discrete spaces. We present a theory for generalized GFlowNets, which encompasses both existing discrete GFlowNets and ones with continuous or hybrid state spaces, and perform experiments with two goals in mind. First, we illustrate critical points of the theory and the importance of various assumptions. Second, we empirically demonstrate how observations about discrete GFlowNets transfer to the continuous case and show strong results compared to non-GFlowNet baselines on several previously studied tasks. This work greatly widens the perspectives for the application of GFlowNets in probabilistic inference and various modeling settings.

2023-07-24

International Conference on Machine Learning (Accept (Poster))

doi.org

proceedings.mlr.press

La plateforme Mila Ventures

Boussole des politiques en IA

Séances d'information virtuelles

Alex Hernández-García

Biographie

Étudiants actuels

Publications

La plateforme Mila Ventures

Boussole des politiques en IA

Séances d'information virtuelles

Mots-clés populaires:

Alex Hernández-García

Biographie

Étudiants actuels

Publications