AdaProb: Efficient Machine Unlearning via Adaptive Probability

[2411.02622] AdaProb: Efficient Machine Unlearning via Adaptive Probability Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2411.02622 (cs) [Submitted on 4 Nov 2024 ( v1 ), last revised 9 Apr 2026 (this version, v3)] Title: AdaProb: Efficient Machine Unlearning via Adaptive Probability Authors: Zihao Zhao , Yuchen Yang , Anjalie Field , Yinzhi Cao View a PDF of the paper titled AdaProb: Efficient Machine Unlearning via Adaptive Probability, by Zihao Zhao and 3 other authors View PDF HTML (experimental) Abstract: Machine unlearning, enabling a trained model to forget specific data, is crucial for addressing erroneous data and adhering to privacy regulations like the General Data Protection Regulation (GDPR)'s "right to be forgotten". Despite recent progress, existing methods face two key challenges: residual information may persist in the model even after unlearning, and the computational overhead required for effective data removal is often high. To address these issues, we propose Adaptive Probability Approximate Unlearning (AdaProb), a novel method that enables models to forget data efficiently and in a privacy-preserving manner. Our method firstly replaces the neural network's final-layer output probabilities with pseudo-probabilities for data to be forgotten. These pseudo-probabilities follow a uniform distribution to maximize unlearning, and they are optimized to align with the model's overall distribution to enhance privacy and reduce the risk of membership inference attacks. Then, the model's weights are updated accordingly. Through comprehensive experiments, our method outperforms state-of-the-art approaches with over 20% improvement in forgetting error, better protection against membership inference attacks, and less than 50% of the computational time. Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2411.02622 [cs.LG] (or arXiv:2411.02622v3 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2411.02622 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Zihao Zhao [ view email ] [v1] Mon, 4 Nov 2024 21:27:06 UTC (886 KB) [v2] Tue, 7 Apr 2026 20:04:24 UTC (873 KB) [v3] Thu, 9 Apr 2026 02:59:33 UTC (873 KB) Full-text links: Access Paper: View a PDF of the paper titled AdaProb: Efficient Machine Unlearning via Adaptive Probability, by Zihao Zhao and 3 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2024-11 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• PeTeR: Post-Training Robustification of Probabilistic Circuits#349619
• BatchGen: An Architecture for Scalable and Efficient Batch Inference#299901
• Behemoth: Benchmarking unlearning in LLMs using fully synthetic data#208831
• KLineage: Recovering the Missing When of Kernel Optimization by Deoptimizing Experts#1141552
• Neuralyzing the Trace: Selective Representation-Level Unlearning with Contrastive Sparse Autoencoders#1105614