ICLR 2022 accepted papers on Continual learning
24 of the 1,095 papers accepted at ICLR 2022 (2.2%) are on Continual learning, compared with 1.9% at ICLR 2021. They fall into 4 topics.
See ICLR 2022 in the interactive map
Submitting to ICLR? 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 · 18 papers
- New Insights on Reducing Abrupt Representation Change in Online Continual Learning (43 citations)
- Memory Replay with Data Compression for Continual Learning (39 citations)
- Online Coreset Selection for Rehearsal-based Continual Learning (39 citations)
- Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System (37 citations)
- Representational Continuity for Unsupervised Continual Learning (28 citations)
- TRGP: Trust Region Gradient Projection for Continual Learning (22 citations)
- Continual Normalization: Rethinking Batch Normalization for Online Continual Learning (20 citations)
- Information-theoretic Online Memory Selection for Continual Learning (12 citations)
- Continual Learning with Recursive Gradient Optimization (8 citations)
- Model Zoo: A Growing Brain That Learns Continually (8 citations)
- Fortuitous Forgetting in Connectionist Networks (5 citations)
- Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference (5 citations)
and 6 more in the interactive map.
