NeurIPS 2020 accepted papers on Continual learning
20 of the 1,901 papers accepted at NeurIPS 2020 (1.1%) are on Continual learning, compared with 0.9% at NeurIPS 2019. They fall into 1 topics.
See NeurIPS 2020 in the interactive map
Submitting to NeurIPS? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Online and replay-based · 20 papers
- Understanding the Role of Training Regimes in Continual Learning (94 citations)
- Dark Experience for General Continual Learning: a Strong, Simple Baseline (90 citations)
- Coresets via Bilevel Optimization for Continual Learning and Streaming (84 citations)
- Continual Deep Learning by Functional Regularisation of Memorable Past (54 citations)
- Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks (53 citations)
- Organizing recurrent network dynamics by task-computation to enable continual learning (51 citations)
- Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning (49 citations)
- Calibrating CNNs for Lifelong Learning (35 citations)
- Improved Schemes for Episodic Memory-based Lifelong Learning (35 citations)
- Meta-Consolidation for Continual Learning (34 citations)
- Continual Learning in Low-rank Orthogonal Subspaces (32 citations)
- Continual Learning with Node-Importance based Adaptive Group Sparse Regularization (27 citations)
and 8 more in the interactive map.
