Research map / Continual learning / Online and replay-based
On the Plasticity Collapse in Continual Machine Unlearning
Yingdan Shi, Xiang Xu, Kaize Ding, Alfred Hero, Ren Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| unlearn tasks sequentially instead of in isolation (forward failure) | FT, NegGrad+, RL, SalUn, MUNBa · Tiny-ImageNet random data forgetting, VGG-16-BN | forgetting accuracy: approximately 33.2% higher | Hurt |
| unlearn class-wise tasks sequentially | RL and SalUn · Tiny-ImageNet class-wise forgetting, VGG-16-BN | forgetting accuracy of earlier tasks | Hurt |
| more sequential unlearning tasks | parameter update magnitude · Tiny-ImageNet VGG-16-BN | L2 norm of consecutive parameter updates | Hurt |
| recent method MUNBa applied to continual unlearning | MUNBa · Tiny-ImageNet random forgetting | forgetting accuracy | No clear effect |
Closest papers by meaning
- Forgetting Has Neighbors: Localized Collateral Forgetting in Machine Unlearning (NeurIPS 2026 · similarity 0.90)
- When to Forget? Complexity Trade-offs in Machine Unlearning (ICML 2025 · similarity 0.89)
- Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective (ICML 2025 · similarity 0.89)
- Measuring Representational Shifts in Continual Learning: A Linear Transformation Perspective (ICML 2025 · similarity 0.88)
- Learning What to Forget: Improving LLM Unlearning via Learned Token-Level Importance (NeurIPS 2026 · similarity 0.88)
- Towards Understanding Catastrophic Forgetting in Two-layer Convolutional Neural Networks (ICML 2025 · similarity 0.88)
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.
