Timezone: »
Continual learning, the setting where a learning agent is faced with a never-ending stream of data, continues to be a great challenge for modern machine learning systems. In particular the online or "single-pass through the data" setting has gained attention recently as a natural setting that is difficult to tackle. Methods based on replay, either generative or from a stored memory, have been shown to be effective approaches for continual learning, matching or exceeding the state of the art in a number of standard benchmarks. These approaches typically rely on randomly selecting samples from the replay memory or from a generative model, which is suboptimal. In this work, we consider a controlled sampling of memories for replay. We retrieve the samples which are most interfered, i.e. whose prediction will be most negatively impacted by the foreseen parameters update. We show a formulation for this sampling criterion in both the generative replay and the experience replay setting, producing consistent gains in performance and greatly reduced forgetting. We release an implementation of our method at https://github.com/optimass/MaximallyInterferedRetrieval
Author Information
Rahaf Aljundi (KU Leuven, Belgium)
Eugene Belilovsky (Mila, University of Montreal)
Tinne Tuytelaars (KU Leuven)
Laurent Charlin (MILA / U.Montreal)
Massimo Caccia (MILA)
Min Lin (MILA)
Lucas Page-Caccia (McGill University)
More from the Same Authors
-
2022 : Poly-S: Analyzing and Improving Polytropon for Data-Efficient Multi-Task Learning »
Lucas Page-Caccia · Edoardo Maria Ponti · Liyuan Liu · Matheus Pereira · Nicolas Le Roux · Alessandro Sordoni -
2022 : Attention for Compositional Modularity »
Oleksiy Ostapenko · Pau Rodriguez · Alexandre Lacoste · Laurent Charlin -
2022 : Reducing Forgetting in Federated Learning with Truncated Cross-Entropy »
Gwen Legate · Lucas Page-Caccia · Eugene Belilovsky -
2022 : Mutual Information Regularized Offline Reinforcement Learning »
Xiao Ma · Bingyi Kang · Zhongwen Xu · Min Lin · Shuicheng Yan -
2022 : Imitation from Observation With Bootstrapped Contrastive Learning »
Medric Sonwa · Johanna Hansen · Eugene Belilovsky -
2022 : HloEnv: A Graph Rewrite Environment for Deep Learning Compiler Optimization Research »
Chin Yang Oh · Kunhao Zheng · Bingyi Kang · Xinyi Wan · Zhongwen Xu · Shuicheng Yan · Min Lin · Yangzihao Wang -
2022 : Building a Subspace of Policies for Scalable Continual Learning »
Jean-Baptiste Gaya · Thang Long Doan · Lucas Page-Caccia · Laure Soulier · Ludovic Denoyer · Roberta Raileanu -
2022 : Imitation from Observation With Bootstrapped Contrastive Learning »
Medric Sonwa · Johanna Hansen · Eugene Belilovsky -
2022 : Deceiving the CKA Similarity Measure in Deep Learning »
MohammadReza Davari · Stefan Horoi · Amine Natik · Guillaume Lajoie · Guy Wolf · Eugene Belilovsky -
2022 : Adversarial Attacks on Feature Visualization Methods »
Michael Eickenberg · Eugene Belilovsky · Jonathan Marty -
2022 : FQDet: Fast-converging Query-based Detector »
Cédric Picron · Punarjay Chakravarty · Tinne Tuytelaars -
2022 : Panel »
Tyler Hayes · Tinne Tuytelaars · Subutai Ahmad · João Sacramento · Zsolt Kira · Hava Siegelmann · Christopher Summerfield -
2022 Poster: EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine »
Jiayi Weng · Min Lin · Shengyi Huang · Bo Liu · Denys Makoviichuk · Viktor Makoviychuk · Zichen Liu · Yufan Song · Ting Luo · Yukun Jiang · Zhongwen Xu · Shuicheng Yan -
2021 : Machine Learning for Combinatorial Optimization + Q&A »
Maxime Gasse · Simon Bowly · Chris Cameron · Quentin Cappart · Jonas Charfreitag · Laurent Charlin · Shipra Agrawal · Didier Chetelat · Justin Dumouchelle · Ambros Gleixner · Aleksandr Kazachkov · Elias Khalil · Pawel Lichocki · Andrea Lodi · Miles Lubin · Christopher Morris · Dimitri Papageorgiou · Augustin Parjadis · Sebastian Pokutta · Antoine Prouvost · Yuandong Tian · Lara Scavuzzo · Giulia Zarpellon -
2021 Poster: Continual Learning via Local Module Composition »
Oleksiy Ostapenko · Pau Rodriguez · Massimo Caccia · Laurent Charlin -
2021 Poster: Pretraining Representations for Data-Efficient Reinforcement Learning »
Max Schwarzer · Nitarshan Rajkumar · Michael Noukhovitch · Ankesh Anand · Laurent Charlin · R Devon Hjelm · Philip Bachman · Aaron Courville -
2021 Poster: How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness? »
Xinshuai Dong · Anh Tuan Luu · Min Lin · Shuicheng Yan · Hanwang Zhang -
2021 Poster: Learning where to learn: Gradient sparsity in meta and continual learning »
Johannes von Oswald · Dominic Zhao · Seijin Kobayashi · Simon Schug · Massimo Caccia · Nicolas Zucchet · João Sacramento -
2020 Poster: Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning »
Massimo Caccia · Pau Rodriguez · Oleksiy Ostapenko · Fabrice Normandin · Min Lin · Lucas Page-Caccia · Issam Hadj Laradji · Irina Rish · Alexandre Lacoste · David Vázquez · Laurent Charlin -
2020 Poster: Synbols: Probing Learning Algorithms with Synthetic Datasets »
Alexandre Lacoste · Pau Rodríguez López · Frederic Branchaud-Charron · Parmida Atighehchian · Massimo Caccia · Issam Hadj Laradji · Alexandre Drouin · Matthew Craddock · Laurent Charlin · David Vázquez -
2020 Session: Orals & Spotlights Track 16: Continual/Meta/Misc Learning »
Laurent Charlin · Cedric Archambeau -
2019 Poster: Gradient based sample selection for online continual learning »
Rahaf Aljundi · Min Lin · Baptiste Goujaud · Yoshua Bengio -
2019 Poster: Exact Combinatorial Optimization with Graph Convolutional Neural Networks »
Maxime Gasse · Didier Chetelat · Nicola Ferroni · Laurent Charlin · Andrea Lodi -
2018 : Poster Session 1 (note there are numerous missing names here, all papers appear in all poster sessions) »
Akhilesh Gotmare · Kenneth Holstein · Jan Brabec · Michal Uricar · Kaleigh Clary · Cynthia Rudin · Sam Witty · Andrew Ross · Shayne O'Brien · Babak Esmaeili · Jessica Forde · Massimo Caccia · Ali Emami · Scott Jordan · Bronwyn Woods · D. Sculley · Rebekah Overdorf · Nicolas Le Roux · Peter Henderson · Brandon Yang · Tzu-Yu Liu · David Jensen · Niccolo Dalmasso · Weitang Liu · Paul Marc TRICHELAIR · Jun Ki Lee · Akanksha Atrey · Matt Groh · Yotam Hechtlinger · Emma Tosch -
2018 Poster: Towards Deep Conversational Recommendations »
Raymond Li · Samira Ebrahimi Kahou · Hannes Schulz · Vincent Michalski · Laurent Charlin · Chris Pal -
2017 Poster: Pose Guided Person Image Generation »
Liqian Ma · Xu Jia · Qianru Sun · Bernt Schiele · Tinne Tuytelaars · Luc Van Gool -
2016 Poster: Dynamic Filter Networks »
Xu Jia · Bert De Brabandere · Tinne Tuytelaars · Luc V Gool -
2014 Poster: Content-based recommendations with Poisson factorization »
Prem Gopalan · Laurent Charlin · David Blei -
2006 Poster: Automated Hierarchy Discovery for Planning in Partially Observable Domains »
Laurent Charlin · Pascal Poupart · Romy Shioda