2 code implementations • 12 Mar 2024 • Alexandre Drouin, Maxime Gasse, Massimo Caccia, Issam H. Laradji, Manuel Del Verme, Tom Marty, Léo Boisvert, Megh Thakkar, Quentin Cappart, David Vazquez, Nicolas Chapados, Alexandre Lacoste
We study the use of large language model-based agents for interacting with software via web browsers.
no code implementations • 25 Apr 2023 • Massimo Caccia, Alexandre Galashov, Arthur Douillard, Amal Rannen-Triki, Dushyant Rao, Michela Paganini, Laurent Charlin, Marc'Aurelio Ranzato, Razvan Pascanu
The field of transfer learning is undergoing a significant shift with the introduction of large pretrained models which have demonstrated strong adaptability to a variety of downstream tasks.
1 code implementation • 15 Nov 2022 • Jorg Bornschein, Alexandre Galashov, Ross Hemsley, Amal Rannen-Triki, Yutian Chen, Arslan Chaudhry, Xu Owen He, Arthur Douillard, Massimo Caccia, Qixuang Feng, Jiajun Shen, Sylvestre-Alvise Rebuffi, Kitty Stacpoole, Diego de Las Casas, Will Hawkins, Angeliki Lazaridou, Yee Whye Teh, Andrei A. Rusu, Razvan Pascanu, Marc'Aurelio Ranzato
A shared goal of several machine learning communities like continual learning, meta-learning and transfer learning, is to design algorithms and models that efficiently and robustly adapt to unseen tasks.
2 code implementations • 28 May 2022 • Massimo Caccia, Jonas Mueller, Taesup Kim, Laurent Charlin, Rasool Fakoor
We pose two hypotheses: (1) task-agnostic methods might provide advantages in settings with limited data, computation, or high dimensionality, and (2) faster adaptation may be particularly beneficial in continual learning settings, helping to mitigate the effects of catastrophic forgetting.
1 code implementation • NeurIPS 2021 • Oleksiy Ostapenko, Pau Rodriguez, Massimo Caccia, Laurent Charlin
We introduce local module composition (LMC), an approach to modular CL where each module is provided a local structural component that estimates a module's relevance to the input.
1 code implementation • NeurIPS 2021 • Johannes von Oswald, Dominic Zhao, Seijin Kobayashi, Simon Schug, Massimo Caccia, Nicolas Zucchet, João Sacramento
We find that patterned sparsity emerges from this process, with the pattern of sparsity varying on a problem-by-problem basis.
no code implementations • ICLR 2022 • Tongtong Wu, Massimo Caccia, Zhuang Li, Yuan-Fang Li, Guilin Qi, Gholamreza Haffari
In this paper, we thoroughly compare the continual learning performance over the combination of 5 PLMs and 4 veins of CL methods on 3 benchmarks in 2 typical incremental settings.
3 code implementations • 2 Aug 2021 • Fabrice Normandin, Florian Golemo, Oleksiy Ostapenko, Pau Rodriguez, Matthew D Riemer, Julio Hurtado, Khimya Khetarpal, Ryan Lindeborg, Lucas Cecchi, Timothée Lesort, Laurent Charlin, Irina Rish, Massimo Caccia
We propose a taxonomy of settings, where each setting is described as a set of assumptions.
no code implementations • 4 Apr 2021 • Timothée Lesort, Massimo Caccia, Irina Rish
In this paper, we aim to identify and categorize different types of context drifts and potential assumptions about them, to better characterize various continual-learning scenarios.
2 code implementations • ICCV 2021 • Pau Rodriguez, Massimo Caccia, Alexandre Lacoste, Lee Zamparo, Issam Laradji, Laurent Charlin, David Vazquez
Explainability for machine learning models has gained considerable attention within the research community given the importance of deploying more reliable machine-learning systems.
no code implementations • 1 Jan 2021 • Pau Rodriguez, Massimo Caccia, Alexandre Lacoste, Lee Zamparo, Issam H. Laradji, Laurent Charlin, David Vazquez
In computer vision applications, most methods explain models by displaying the regions in the input image that they focus on for their prediction, but it is difficult to improve models based on these explanations since they do not indicate why the model fail.
no code implementations • NeurIPS 2020 • Massimo Caccia, Pau Rodriguez, Oleksiy Ostapenko, Fabrice Normandin, Min Lin, Lucas Page-Caccia, Issam Hadj Laradji, Irina Rish, Alexandre Lacoste, David Vázquez, Laurent Charlin
The main challenge is that the agent must not forget previous tasks and also adapt to novel tasks in the stream.
4 code implementations • NeurIPS 2020 • Alexandre Lacoste, Pau Rodríguez, Frédéric Branchaud-Charron, Parmida Atighehchian, Massimo Caccia, Issam Laradji, Alexandre Drouin, Matt Craddock, Laurent Charlin, David Vázquez
Progress in the field of machine learning has been fueled by the introduction of benchmark datasets pushing the limits of existing algorithms.
1 code implementation • 14 Sep 2020 • Vincenzo Lomonaco, Lorenzo Pellegrini, Pau Rodriguez, Massimo Caccia, Qi She, Yu Chen, Quentin Jodelet, Ruiping Wang, Zheda Mai, David Vazquez, German I. Parisi, Nikhil Churamani, Marc Pickett, Issam Laradji, Davide Maltoni
In the last few years, we have witnessed a renewed and fast-growing interest in continual learning with deep neural networks with the shared objective of making current AI systems more adaptive, efficient and autonomous.
1 code implementation • NeurIPS 2020 • Massimo Caccia, Pau Rodriguez, Oleksiy Ostapenko, Fabrice Normandin, Min Lin, Lucas Caccia, Issam Laradji, Irina Rish, Alexandre Lacoste, David Vazquez, Laurent Charlin
We propose Continual-MAML, an online extension of the popular MAML algorithm as a strong baseline for this scenario.
2 code implementations • NeurIPS 2019 • Rahaf Aljundi, Eugene Belilovsky, Tinne Tuytelaars, Laurent Charlin, Massimo Caccia, Min Lin, Lucas Page-Caccia
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.
1 code implementation • ICML 2020 • Lucas Caccia, Eugene Belilovsky, Massimo Caccia, Joelle Pineau
We show how to use discrete auto-encoders to effectively address this challenge and introduce Adaptive Quantization Modules (AQM) to control variation in the compression ability of the module at any given stage of learning.
no code implementations • 25 Sep 2019 • Lucas Caccia, Eugene Belilovsky, Massimo Caccia, Joelle Pineau
We first replace the episodic memory used in Experience Replay with SQM, leading to significant gains on standard continual learning benchmarks using a fixed memory budget.
1 code implementation • 11 Aug 2019 • Rahaf Aljundi, Lucas Caccia, Eugene Belilovsky, Massimo Caccia, Min Lin, Laurent Charlin, Tinne Tuytelaars
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.
1 code implementation • ICLR 2020 • Massimo Caccia, Lucas Caccia, William Fedus, Hugo Larochelle, Joelle Pineau, Laurent Charlin
Generating high-quality text with sufficient diversity is essential for a wide range of Natural Language Generation (NLG) tasks.
1 code implementation • 7 Jul 2017 • Massimo Caccia, Bruno Rémillard
In this paper we solve the discrete time mean-variance hedging problem when asset returns follow a multivariate autoregressive hidden Markov model.