David Rolnick

Biographie

David Rolnick est professeur adjoint et titulaire d’une chaire en IA Canada-CIFAR à l'École d'informatique de l'Université McGill et membre académique principal de Mila – Institut québécois d’intelligence artificielle. Ses travaux portent sur les applications de l'apprentissage automatique dans la lutte contre le changement climatique. Il est cofondateur et président de Climate Change AI et codirecteur scientifique de Sustainability in the Digital Age. David Rolnick a obtenu un doctorat en mathématiques appliquées du Massachusetts Institute of Technology (MIT). Il a été chercheur postdoctoral en sciences mathématiques à la National Science Foundation (NSF), chercheur diplômé à la NSF et boursier Fulbright. Il a figuré sur la liste des « 35 innovateurs de moins de 35 ans » de la MIT Technology Review en 2021.

Étudiants actuels

Benjamin Akera Binen

Collaborateur·rice alumni - McGill

Collaborateur·rice alumni - UdeM

Mohit Anand

Collaborateur·rice de recherche - The University of Dresden, Helmholtz Centre for Environmental Research Leipzig

Ayush Ayush Prasad

Collaborateur·rice de recherche

Viktoriia Baibakova

Collaborateur·rice de recherche

Nikolaos Ioannis Bountos

Collaborateur·rice de recherche - National Observatory of Athens

Collaborateur·rice de recherche

Michael Bunsen

Collaborateur·rice de recherche - McGill

Juan Sebastián Cañas

Collaborateur·rice de recherche

Collaborateur·rice de recherche - N/A

Co-superviseur⋅e :

Yuyan Chen

Maîtrise recherche - McGill

Eya Cherif

Stagiaire de recherche - Leipzig University

Alexandre Duval

Collaborateur·rice de recherche - Université Paris-Saclay

Amna El-Mustafa

Collaborateur·rice de recherche

Paula Harder

Collaborateur·rice de recherche

Alex Hernandez-Garcia

Postdoctorat - UdeM

Superviseur⋅e principal⋅e :

Collaborateur·rice de recherche - UdeM

Christina Humer

Collaborateur·rice de recherche - Johannes Kepler University

Gaurav Iyer

Maîtrise recherche - McGill

Doctorat - McGill

Devin Kwok

Doctorat - McGill

Vanessa Mac

Collaborateur·rice de recherche - University of Waterloo

David Alexandre Mickisch

Collaborateur·rice de recherche

Felix Andreas Nahrstedt

Stagiaire de recherche - UdeM

Arthur Ouaknine

Postdoctorat - McGill

Co-superviseur⋅e :

Lena Podina

Doctorat - University of Waterloo

Co-superviseur⋅e :

Doctorat - UdeM

Collaborateur·rice de recherche

Marlena Reil

Maîtrise recherche - McGill

Pratinav Seth

Collaborateur·rice de recherche

seth.pratinav@gmail.com

Collaborateur·rice de recherche - RWTH Aachen University (Rheinisch-Westfälische Technische Hochschule Aachen)

Co-superviseur⋅e :

Ilija Trajković

Collaborateur·rice de recherche - Karlsruhe Institute of Technology

Doctorat - McGill

Postdoctorat - UdeM

Superviseur⋅e principal⋅e :

Collaborateur·rice de recherche

anna.viklund@mila.quebec

Doctorat - McGill

Collaborateur·rice alumni - McGill

Gintare Karolina Dziugaite

Qidong Yang

Collaborateur·rice de recherche

qidong.yang@mila.quebec

Publications

Dataset Difficulty and the Role of Inductive Bias

Devin Kwok

Nikhil Anand

Jonathan Frankle

Motivated by the goals of dataset pruning and defect identification, a growing body of methods have been developed to score individual examp… (voir plus)les within a dataset. These methods, which we call"example difficulty scores", are typically used to rank or categorize examples, but the consistency of rankings between different training runs, scoring methods, and model architectures is generally unknown. To determine how example rankings vary due to these random and controlled effects, we systematically compare different formulations of scores over a range of runs and model architectures. We find that scores largely share the following traits: they are noisy over individual runs of a model, strongly correlated with a single notion of difficulty, and reveal examples that range from being highly sensitive to insensitive to the inductive biases of certain model architectures. Drawing from statistical genetics, we develop a simple method for fingerprinting model architectures using a few sensitive examples. These findings guide practitioners in maximizing the consistency of their scores (e.g. by choosing appropriate scoring methods, number of runs, and subsets of examples), and establishes comprehensive baselines for evaluating scores in the future.

2024-01-03

ArXiv (prépublication)

Application-Driven Innovation in Machine Learning

Alan Aspuru-Guzik

Sara Beery

Bistra Dilkina

Priya L. Donti

Marzyeh Ghassemi

Hannah Kerner

Claire Monteleoni

Esther Rolf

Milind Tambe

Adam White

As applications of machine learning proliferate, innovative algorithms inspired by specific real-world challenges have become increasingly i… (voir plus)mportant. Such work offers the potential for significant impact not merely in domains of application but also in machine learning itself. In this paper, we describe the paradigm of application-driven research in machine learning, contrasting it with the more standard paradigm of methods-driven research. We illustrate the benefits of application-driven machine learning and how this approach can productively synergize with methods-driven work. Despite these benefits, we find that reviewing, hiring, and teaching practices in machine learning often hold back application-driven innovation. We outline how these processes may be improved.

2024-01-01

ICML (publié)

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

Alexandre AGM Duval

Victor Schmidt

Santiago Miret

Alex Hernandez-Garcia

openreview.net

Simultaneous linear connectivity of neural networks modulo permutation

Ekansh Sharma

Devin Kwok

Tom Denton

Daniel M. Roy

Gintare Karolina Dziugaite

2024-01-01

ECML/PKDD (7) (publié)

A landmark environmental law looks ahead

Robert L. Fischman

J. B. Ruhl

Brenna R. Forester

Tanya M. Lama

Marty Kardos

Grethel Aguilar Rojas

Nicholas A. Robinson

Patrick D. Shirey

Gary A. Lamberti

Amy W. Ando

Stephen Palumbi

Michael Wara

Mark W. Schwartz

Matthew A. Williamson

Tanya Berger-Wolf

Sara Beery

Justin Kitzes

David Thau

Devis Tuia … (voir 8 de plus)

Daniel Rubenstein

Caleb R. Hickman

Julie Thorstenson

Gregory E. Kaebnick

James P. Collins

Athmeya Jayaram

Thomas Deleuil

Ying Zhao

2023-12-22

Science (publié)

FoMo-Bench: a multi-modal, multi-scale and multi-task Forest Monitoring Benchmark for remote sensing foundation models

Nikolaos Ioannis Bountos

Arthur Ouaknine

2023-12-15

ArXiv (prépublication)

Towards Causal Representations of Climate Model Data

Julien Boussard

Chandni Nagda

Julia Kaltenborn

Charlotte Emilie Elektra Lange

Philippe Brouillard

Yaniv Gurwicz

Peer Nowack

Climate models, such as Earth system models (ESMs), are crucial for simulating future climate change based on projected Shared Socioeconomic… (voir plus) Pathways (SSP) greenhouse gas emissions scenarios. While ESMs are sophisticated and invaluable, machine learning-based emulators trained on existing simulation data can project additional climate scenarios much faster and are computationally efficient. However, they often lack generalizability and interpretability. This work delves into the potential of causal representation learning, specifically the \emph{Causal Discovery with Single-parent Decoding} (CDSD) method, which could render climate model emulation efficient \textit{and} interpretable. We evaluate CDSD on multiple climate datasets, focusing on emissions, temperature, and precipitation. Our findings shed light on the challenges, limitations, and promise of using CDSD as a stepping stone towards more interpretable and robust climate model emulation.

2023-12-05

ArXiv (prépublication)

SatBird: Bird Species Distribution Modeling with Remote Sensing and Citizen Science Data

Mélisande Teng

Amna Elmustafa

Benjamin Akera

Hager Radi

Hugo Larochelle

Biodiversity is declining at an unprecedented rate, impacting ecosystem services necessary to ensure food, water, and human health and well-… (voir plus)being. Understanding the distribution of species and their habitats is crucial for conservation policy planning. However, traditional methods in ecology for species distribution models (SDMs) generally focus either on narrow sets of species or narrow geographical areas and there remain significant knowledge gaps about the distribution of species. A major reason for this is the limited availability of data traditionally used, due to the prohibitive amount of effort and expertise required for traditional field monitoring. The wide availability of remote sensing data and the growing adoption of citizen science tools to collect species observations data at low cost offer an opportunity for improving biodiversity monitoring and enabling the modelling of complex ecosystems. We introduce a novel task for mapping bird species to their habitats by predicting species encounter rates from satellite images, and present SatBird, a satellite dataset of locations in the USA with labels derived from presence-absence observation data from the citizen science database eBird, considering summer (breeding) and winter seasons. We also provide a dataset in Kenya representing low-data regimes. We additionally provide environmental data and species range maps for each location. We benchmark a set of baselines on our dataset, including SOTA models for remote sensing tasks. SatBird opens up possibilities for scalably modelling properties of ecosystems worldwide.

2023-11-02

ArXiv (prépublication)

OpenForest: A data catalogue for machine learning in forest monitoring

Arthur Ouaknine

Teja Kattenborn

Etienne Lalibert'e

2023-11-01

ArXiv (prépublication)

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

Alvaro Carbonero

Alexandre AGM Duval

Victor Schmidt

Santiago Miret

Alex Hernandez-Garcia

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.

2023-10-27

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

openreview.net

ClimateSet: A Large-Scale Climate Model Dataset for Machine Learning

Julia Kaltenborn

Charlotte Emilie Elektra Lange

Venkatesh Ramesh

Philippe Brouillard

Yaniv Gurwicz

Chandni Nagda

Jakob Runge

Peer Nowack