NeurIPS 2022 accepted papers on Continual learning
34 of the 2,901 papers accepted at NeurIPS 2022 (1.2%) are on Continual learning, compared with 1.2% at NeurIPS 2021. They fall into 4 topics.
See NeurIPS 2022 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
- Task-Free Continual Learning via Online Discrepancy Distance Learning (20 citations)
- On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learning (16 citations)
- Exploring Example Influence in Continual Learning (15 citations)
- SparCL: Sparse Continual Learning on the Edge (15 citations)
- A simple but strong baseline for online continual learning: Repeated Augmented Rehearsal (12 citations)
- An Analytical Theory of Curriculum Learning in Teacher-Student Networks (8 citations)
- Beyond Not-Forgetting: Continual Learning with Backward Knowledge Transfer (8 citations)
- CGLB: Benchmark Tasks for Continual Graph Learning (7 citations)
- How Well Do Unsupervised Learning Algorithms Model Human Real-time and Life-long Learning? (7 citations)
- Characterizing Datapoints via Second-Split Forgetting (3 citations)
- TempEL: Linking Dynamically Evolving and Newly Emerging Entities (3 citations)
- BayesPCN: A Continually Learnable Predictive Coding Associative Memory (2 citations)
and 8 more in the interactive map.
Class-incremental · 9 papers
- Remember the Past: Distilling Datasets into Addressable Memories for Neural Networks (21 citations)
- A Theoretical Study on Solving Continual Learning (16 citations)
- Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation (16 citations)
- ACIL: Analytic Class-Incremental Learning with Absolute Memorization and Privacy Protection (15 citations)
- Few-Shot Continual Active Learning by a Robot (12 citations)
- Mining Unseen Classes via Regional Objectness: A Simple Baseline for Incremental Segmentation (12 citations)
- ALIFE: Adaptive Logit Regularizer and Feature Replay for Incremental Semantic Segmentation (10 citations)
- Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentation (8 citations)
- Continual Learning with Evolving Class Ontologies (2 citations)
