awesome-machine-unlearning
github.com/tamlhp/awesome-machine-unlearning ↗Awesome Machine Unlearning (A Survey of Machine Unlearning)
954
GitHub Stars
265
Curated Resources
5
Categories
4 hours ago
Last Refreshed
Existing SurveysModel-Agnostic ApproachesModel-Intrinsic ApproachesData-Driven ApproachesDatasets
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me type: sequence resources from awesome-machine-unlearning"
Installation instructions →What's inside
Model-Intrinsic Approaches
- Active forgetting via influence estimation for neural networks
2022
- Adapt then Unlearn: Exploiting Parameter Space Semantics for Unlearning in Generative Adversarial Networks
2023
- Alternate Preference Optimization for Unlearning Factual Knowledge in Large Language Models
2025
- “Amnesia” – Towards Machine Learning Models That Can Forget User Data Very Fast
2019
- An Adversarial Perspective on Machine Unlearning for AI Safety
2024
- A Novel Online Incremental and Decremental Learning Algorithm Based on Variable Support Vector Machine
2019
Datasets
- Activity RecognitionType: Sequence
- AdultType: Tabular
- BotnetType: Sequence
- Breast CancerType: Tabular
- CIFARType: Image
- CoraType: Graph
Model-Agnostic Approaches
- Adaptive Machine Unlearning
2021
- Athena: Probabilistic Verification of Machine Unlearning
2022
- Backdoor Defense with Machine Unlearning
2022
- CaMU: Disentangling Causal Effects in Deep Model Unlearning
2024
- Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher
2022
- Certified Data Removal in Sum-Product Networks
2022
Existing Surveys
- Algorithms that remember: model inversion attacks and data protection law
Philosophical Transactions of the Royal Society A
- “Amnesia” - A Selection of Machine Learning Models That Can Forget User Data Very Fast
CIDR
- An Introduction to Machine Unlearning
arXiv
- A Survey of Federated Unlearning: A Taxonomy, Challenges and Future Directions
arXiv
- A Survey on Federated Unlearning: Challenges, Methods, and Future Directions
arXiv
- Digital Forgetting in Large Language Models: A Survey of Unlearning Methods
arXiv
Data-Driven Approaches
- Amnesiac Machine Learning
2021
- ARCANE: An Efficient Architecture for Exact Machine Unlearning
2022
- Certifiable Unlearning Pipelines for Logistic Regression: An Experimental Study
2022
- Coded Machine Unlearning
2021
- DeltaGrad: Rapid retraining of machine learning models
2020
- Descent-to-Delete: Gradient-Based Methods for Machine Unlearning
2021
Showing a sample of 265 resources. View the full list on GitHub →