Publications

Generalizable Imitation Learning Through Pre-Trained Representations

Wei-Di Chang

Francois Hogan

In this paper we leverage self-supervised vision transformer models and their emergent semantic abilities to improve the generalization abil… (voir plus)ities of imitation learning policies. We introduce BC-ViT, an imitation learning algorithm that leverages rich DINO pre-trained Visual Transformer (ViT) patch-level embeddings to obtain better generalization when learning through demonstrations. Our learner sees the world by clustering appearance features into semantic concepts, forming stable keypoints that generalize across a wide range of appearance variations and object types. We show that this representation enables generalized behaviour by evaluating imitation learning across a diverse dataset of object manipulation tasks. Our method, data and evaluation approach are made available to facilitate further study of generalization in Imitation Learners.

2023-11-15

ArXiv (prépublication)

doi.org

arxiv.org

Adaptive Integration of Categorical and Multi-relational Ontologies with EHR Data for Medical Concept Embedding

Chin Wang Cheong

Kejing Yin

William K. Cheung

Benjamin Fung

Jonathan Poon

2023-11-14

ACM Transactions on Intelligent Systems and Technology (publié)

doi.org

A community effort in SARS-CoV-2 drug discovery.

Johannes Schimunek

Philipp Seidl

Katarina Elez

Tim Hempel

Tuan Le

Frank Noé

Simon Olsson

Lluís Raich

Robin Winter

Hatice Gokcan

Filipp Gusev

Evgeny M. Gutkin

Olexandr Isayev

Maria G. Kurnikova

Chamali H. Narangoda

Roman Zubatyuk

Ivan P. Bosko

Konstantin V. Furs

Anna D. Karpenko

Yury V. Kornoushenko … (voir 133 de plus)

Mikita Shuldau

Artsemi Yushkevich

Mohammed B. Benabderrahmane

Patrick Bousquet‐Melou

Ronan Bureau

Beatrice Charton

Bertrand C. Cirou

Gérard Gil

William J. Allen

Suman Sirimulla

Stanley Watowich

Nick Antonopoulos

Nikolaos Epitropakis

Agamemnon Krasoulis

Vassilis Pitsikalis

Stavros Theodorakis

Igor Kozlovskii

Anton Maliutin

Alexander Medvedev

Petr Popov

Mark Zaretckii

Hamid Eghbal‐Zadeh

Christina Halmich

Sepp Hochreiter

Andreas Mayr

Peter Ruch

Michael Widrich

Francois Berenger

Ashutosh Kumar

Yoshihiro Yamanishi

Kam Y. J. Zhang

Emmanuel Bengio

Yoshua Bengio

Moksh J. Jain

Maksym Korablyov

Cheng-Hao Liu

Gilles Marcou

Marcous Gilles

Enrico Glaab

Kelly Barnsley

Suhasini M. Iyengar

Mary Jo Ondrechen

V. Joachim Haupt

Florian Kaiser

Michael Schroeder

Luisa Pugliese

Simone Albani

Christina Athanasiou

Andrea Beccari

Paolo Carloni

Giulia D'Arrigo

Eleonora Gianquinto

Jonas Goßen

Anton Hanke

Benjamin P. Joseph

Daria B. Kokh

Sandra Kovachka

Candida Manelfi

Goutam Mukherjee

Abraham Muñiz‐Chicharro

Francesco Musiani

Ariane Nunes‐Alves

Giulia Paiardi

Giulia Rossetti

S. Kashif Sadiq

Francesca Spyrakis

Carmine Talarico

Alexandros Tsengenes

Rebecca C. Wade

Conner Copeland

Jeremiah Gaiser

Daniel R. Olson

Amitava Roy

Vishwesh Venkatraman

Travis J. Wheeler

Haribabu Arthanari

Klara Blaschitz

Marco Cespugli

Vedat Durmaz

Konstantin Fackeldey

Patrick D. Fischer

Christoph Gorgulla

Christian Gruber

Karl Gruber

Michael Hetmann

Jamie E. Kinney

Krishna M. Padmanabha Das

Shreya Pandita

Amit Singh

Georg Steinkellner

Guilhem Tesseyre

Gerhard Wagner

Zi‐Fu Wang

Ryan J. Yust

Dmitry S. Druzhilovskiy

Dmitry A. Filimonov

Pavel V. Pogodin

Vladimir Poroikov

Anastassia V. Rudik

Leonid A. Stolbov

Alexander V. Veselovsky

Maria De Rosa

Giada De Simone

Maria R. Gulotta

Jessica Lombino

Nedra Mekni

Ugo Perricone

Arturo Casini

Amanda Embree

D. Benjamin Gordon

David Lei

Katelin Pratt

Christopher A. Voigt

Kuang‐Yu Chen

Yves Jacob

Tim Krischuns

Pierre Lafaye

Agnès Zettor

M. Luis Rodríguez

Kris M. White

Daren Fearon

Frank Von Delft

Martin A. Walsh

Dragos Horvath

Charles L. Brooks

Babak Falsafi

Bryan Ford

Adolfo García‐Sastre

Sang Yup Lee

Nadia Naffakh

Alexandre Varnek

Günter Klambauer

Thomas M. Hermans

The COVID-19 pandemic continues to pose a substantial threat to human lives and is likely to do so for years to come. Despite the availabili… (voir plus)ty of vaccines, searching for efficient small-molecule drugs that are widely available, including in low- and middle-income countries, is an ongoing challenge. In this work, we report the results of an open science community effort, the "Billion molecules against Covid-19 challenge", to identify small-molecule inhibitors against SARS-CoV-2 or relevant human receptors. Participating teams used a wide variety of computational methods to screen a minimum of 1 billion virtual molecules against 6 protein targets. Overall, 31 teams participated, and they suggested a total of 639,024 molecules, which were subsequently ranked to find 'consensus compounds'. The organizing team coordinated with various contract research organizations (CROs) and collaborating institutions to synthesize and test 878 compounds for biological activity against proteases (Nsp5, Nsp3, TMPRSS2), nucleocapsid N, RdRP (only the Nsp12 domain), and (alpha) spike protein S. Overall, 27 compounds with weak inhibition/binding were experimentally identified by binding-, cleavage-, and/or viral suppression assays and are presented here. Open science approaches such as the one presented here contribute to the knowledge base of future drug discovery efforts in finding better SARS-CoV-2 treatments.

2023-11-14

Molecular informatics (publié)

doi.org

Language Model-In-The-Loop: Data Optimal Approach to Learn-To-Recommend Actions in Text Games

Arjun Vaithilingam Sudhakar

Prasanna Parthasarathi

Janarthanan Rajendran

Sarath Chandar

2023-11-13

ArXiv (prépublication)

doi.org

arxiv.org

Bridging the Gap Between Offline and Online Reinforcement Learning Evaluation Methodologies

Shiva Kanth Sujit

Pedro Braga

Jorg Bornschein

Samira Ebrahimi Kahou

Reinforcement learning (RL) has shown great promise with algorithms learning in environments with large state and action spaces purely from … (voir plus)scalar reward signals. A crucial challenge for current deep RL algorithms is that they require a tremendous amount of environment interactions for learning. This can be infeasible in situations where such interactions are expensive, such as in robotics. Offline RL algorithms try to address this issue by bootstrapping the learning process from existing logged data without needing to interact with the environment from the very beginning. While online RL algorithms are typically evaluated as a function of the number of environment interactions, there isn't a single established protocol for evaluating offline RL methods. In this paper, we propose a sequential approach to evaluate offline RL algorithms as a function of the training set size and thus by their data efficiency. Sequential evaluation provides valuable insights into the data efficiency of the learning process and the robustness of algorithms to distribution changes in the dataset while also harmonizing the visualization of the offline and online learning phases. Our approach is generally applicable and easy to implement. We compare several existing offline RL algorithms using this approach and present insights from a variety of tasks and offline datasets.

2023-11-10

TMLR (accepté)

doi.org

openreview.net

CD3ζ ITAMs enable ligand discrimination and antagonism by inhibiting TCR signaling in response to low-affinity peptides

Guillaume Gaud

Sooraj R. Achar

François X. P. Bourassa

John S. Davies

Teri Hatzihristidis

Seeyoung Choi

Taisuke Kondo

Selamawit Gossa

Jan Lee

Paul Juneau

Naomi Taylor

Christian S. Hinrichs

Dorian B. McGavern

Paul François

Grégoire Altan-Bonnet

Paul E. Love

2023-11-09

Nature Immunology (publié)

doi.org

Stochastic Mirror Descent: Convergence Analysis and Adaptive Variants via the Mirror Stochastic Polyak Stepsize

Ryan D'Orazio

Nicolas Loizou

Issam Hadj Laradji

Ioannis Mitliagkas

We investigate the convergence of stochastic mirror descent (SMD) under interpolation in relatively smooth and smooth convex optimization. I… (voir plus)n relatively smooth convex optimization we provide new convergence guarantees for SMD with a constant stepsize. For smooth convex optimization we propose a new adaptive stepsize scheme --- the mirror stochastic Polyak stepsize (mSPS). Notably, our convergence results in both settings do not make bounded gradient assumptions or bounded variance assumptions, and we show convergence to a neighborhood that vanishes under interpolation. Consequently, these results correspond to the first convergence guarantees under interpolation for the exponentiated gradient algorithm for fixed or adaptive stepsizes. mSPS generalizes the recently proposed stochastic Polyak stepsize (SPS) (Loizou et al. 2021) to mirror descent and remains both practical and efficient for modern machine learning applications while inheriting the benefits of mirror descent. We complement our results with experiments across various supervised learning tasks and different instances of SMD, demonstrating the effectiveness of mSPS.

2023-11-08

TMLR (accepté)

openreview.net