Accepted Papers

Poster session

The poster session will be hosted in GatherTown, which can be accessed using this link. After you log in, you can find the poster room at the top the conference hall.

Spotlight

• Incremental Learning via Rate Reduction

Ziyang Wu (Cornell University); Christina Baek (UC Berkeley); Chong You (University of California, Berkeley); Yi Ma (UC Berkeley)

• TACOS: Task Agnostic Continual Learning in Spiking Neural Networks

Nicholas Soures (University of Texas San Antonio); Peter S Helfer (UTSA); Anurag Daram (University of Texas, San Antonio); Tej Pandit (University of Texas, San Antonio); Dhireesha Kudithipudi (University of Texas at San Antonio)

• An Empirical Investigation of the Role of Pre-training in Lifelong Learning

Sanket Vaibhav Mehta (Carnegie Mellon University); Darshan Patil (Carnegie Mellon University); Sarath Chandar (Mila / École Polytechnique de Montréal); Emma Strubell (Facebook AI Research)

Poster

• Continual Learning with Embeddings: Algorithm and Analysis

Zhen Wang (The University of Sydney ); Liu Liu (The University of Sydney); Yiqun Duan (University of Technology Sydney); Dacheng Tao (The University of Sydney)

• On the importance of cross-task features for class-incremental learning (supplementary)

Albin Soutif--Cormerais (Computer Vision Center); Marc Masana (Computer Vision Center); Joost van de Weijer (Computer Vision Center); Bartlomiej Twardowski (Computer Vision Center, UAB)

• How do Quadratic Regularizers Prevent Catastrophic Forgetting: The Role of Interpolation

Ekdeep Lubana (University of Michigan); Puja Trivedi (University of Michigan); Danai Koutra (U Michigan); Robert Dick (University of Michigan)

• TAG: Task-based Accumulated Gradients for Lifelong learning

Pranshu Malviya (Indian Institute of Technology, Madras); Balaraman Ravindran (Indian Institute of Technology, Madras); Sarath Chandar (Mila / École Polytechnique de Montréal)

• Learn the Time to Learn: Replay Scheduling for Continual Learning

Marcus Klasson (KTH Royal Institute of Technology); Hedvig Kjellström (KTH Royal Institute of Technology); Cheng Zhang (Microsoft)

• Continual Learning via Function-Space Variational Inference: A Unifying View

Tim G. J. Rudner (University of Oxford); Freddie Bickford Smith (University of Oxford); Qixuan FENG (University of Oxford); Yee Whye Teh (University of Oxford); Yarin Gal (University of Oxford)

• Encoders and Ensembles for Task-Free Continual Learning

Murray P Shanahan (DeepMind); Christos Kaplanis (DeepMind); Jovana Mitrovic (DeepMind)

• A study on the plasticity of neural networks

Tudor Berariu (Imperial College London); Wojciech M Czarnecki (DeepMind); Soham De (DeepMind); Jorg Bornschein (Deepmind); Samuel L Smith (DeepMind); Razvan Pascanu (Google Deepmind); Claudia Clopath (Imperial College London)

• Sequoia - a Software Framework to Unify Continual Learning Research (supplementary)

Fabrice Normandin (Mila); Oleksiy Ostapenko (University of Montreal, Mila); Florian Golemo (Mila, ElementAI); Matthew D Riemer (IBM Research); Pau Rodriguez (Element AI); Khimya Khetarpal (McGill University); Timothee Lesort (Mila / UdeM); Julio Hurtado (Universidad Catolica de Chile); Ryan Lindeborg (Independent); Laurent Charlin (HEC Montreal and Mila); Irina Rish (University of Montreal); Massimo Caccia (Mila)

• Continual learning and Deep Networks: an Analysis of the Last Layer

Timothee Lesort (Mila / UdeM); Thomas George (Mila - Université de Montréal); Irina Rish (University of Montreal)

• Understanding Continual Learning Settings with Data Distribution Drift Analysis

Timothee Lesort (Mila / UdeM); Massimo Caccia (MILA); Irina Rish (Mila/UdeM)

• Lifelong Learning with Sketched Structural Regularization

Haoran Li (Johns Hopkins University); Aditya R Krishnan (Johns Hopkins University); Jingfeng Wu (Johns Hopkins University); Soheil Kolouri (Vanderbilt University); Praveen Pilly (HRL Laboratories LLC); Vladimir Braverman (Johns Hopkins University)