Research map / Continual learning / Online and replay-based
Continual Learning with Node-Importance based Adaptive Group Sparse Regularization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use proximal gradient descent (PGD) updates instead of plain Adam on the group-sparse loss (ablation) | AGS-CL · CIFAR-100 | average accuracy | Helped |
| vary rho from 0.1 to 0.5 (Rand-init) (ablation) | AGS-CL · CIFAR-100 | average accuracy | No clear effect |
| AGS-CL instead of EWC and MAS | continual learning regularization · CIFAR-100 plasticity-stability trade-off | plasticity vs stability trade-off | Helped |
| AGS-CL instead of MAS | continual learning · CIFAR-10/100 | average accuracy (%): 72.1 -> 76.1 | Helped |
Closest papers by meaning
- A Statistical Theory of Regularization-Based Continual Learning (ICML 2024 · similarity 0.88)
- Optimal Rates in Continual Linear Regression via Increasing Regularization (NeurIPS 2025 · similarity 0.88)
- Learning Continually by Spectral Regularization (ICLR 2025 · similarity 0.87)
- Learning to Continually Learn with the Bayesian Principle (ICML 2024 · similarity 0.86)
- Improving Continual Learning Performance and Efficiency with Auxiliary Classifiers (ICML 2025 · similarity 0.86)
- TinySubNets: An Efficient and Low Capacity Continual Learning Strategy (AAAI 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.