Research map / Learning theory and algorithms / Prediction and decision losses
Adaptive Machine Unlearning
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 |
|---|---|---|---|
| Choose deletion requests adaptively based on published model confidence | SISA · CIFAR-10, MNIST, Fashion-MNIST | adaptive deletion guarantee (test statistic) | Hurt |
| Add noise to training gradients | SISA · CIFAR-10, MNIST, Fashion-MNIST | adaptive deletion attack test statistic | Helped |
| Add noise to training gradients | SISA · CIFAR-10, MNIST, Fashion-MNIST | ensemble accuracy | Hurt |
| Publish predictions using aggregation that is differentially private in the internal random seeds | Distributed SISA-style unlearning · Adaptive update sequences | unlearning guarantee | Helped |
| Use independent shards and retrain only shards affected by an update | Distributed SISA-style unlearning · Non-adaptive update sequences | unlearning guarantee | Helped |
Closest papers by meaning
- Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions (NeurIPS 2025 · similarity 0.87)
- Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable (NeurIPS 2024 · similarity 0.86)
- The Utility and Complexity of In- and Out-of-Distribution Machine Unlearning (ICLR 2025 · similarity 0.85)
- Deletion-Anticipative Data Selection with a Limited Budget (ICML 2024 · similarity 0.85)
- A Certified Unlearning Approach without Access to Source Data (ICML 2025 · similarity 0.85)
- System-Aware Unlearning Algorithms: Use Lesser, Forget Faster (ICML 2025 · similarity 0.84)
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.