Lune

AAAI2025顶会

Toward Efficient Data-Free Unlearning

Chenhao Zhang, Shaofei Shen, Weitong Chen, Miao Xu

摘要

Machine unlearning without access to real data distribution is challenging. The existing method based on data-free distillation achieved unlearning by filtering out synthetic samples containing forgetting information but struggled to distill the retaining-related knowledge efficiently. In this work, we analyze that such a problem is due to over-filtering, which reduces the synthesized retaining-related information. We propose a novel method, Inhibited Synthetic PostFilter (ISPF), to tackle this challenge from two perspectives: First, the Inhibited Synthetic, by reducing the synthesized forgetting information; Second, the PostFilter, by fully utilizing the retaining-related information in synthesized samples. Experimental results demonstrate that the proposed ISPF effectively tackles the challenge and outperforms existing methods.

问 Lune

几分钟读透这篇 Paper,不用再花一下午。

Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。

已有 2 篇顶会 Paper 引用了它。别等审稿人问起,先弄清它们发现了什么。

可以从这些问题问起

Lune 可以查阅

全文 · 引用它的顶会 Paper · 相关的 Paper

获取答案

免费开始,无需绑卡

脉络

  • Fast Machine Unlearning without Retraining through Selective Synaptic Dampening 引用了 Membership Inference Attacks Against Machine Learning Models
  • Up to 100x Faster Data-Free Knowledge Distillation 引用了 Data-Free Learning of Student Networks
  • Synthetic Forgetting Without Access: A Few-Shot Zero-Glance Framework for Machine Unlearning 引用了 SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
  • Efficient Source-free Unlearning via Energy-Guided Data Synthesis and Discrimination-Aware Multitask Optimization 引用了 Fast Machine Unlearning without Retraining through Selective Synaptic Dampening
它引用的引用它的从左到右按年份排列,引用越多,位置越高。

引用它的顶会 Paper2

  1. Synthetic Forgetting Without Access: A Few-Shot Zero-Glance Framework for Machine UnlearningQipeng Song, Nan Yang, Ziqi Xu, Yue Li 等AAAI 2026 · 2 次引用
  2. Efficient Source-free Unlearning via Energy-Guided Data Synthesis and Discrimination-Aware Multitask OptimizationXiuyuan Wang, Chaochao Chen, Weiming Liu, Xinting Liao 等ICML 2025

它引用的 Paper10

  1. Membership Inference Attacks Against Machine Learning ModelsReza Shokri, Marco Stronati, Congzheng Song, Vitaly ShmatikovS&P 2017 · 5,137 次引用
  2. Data-Free Learning of Student NetworksHanting Chen, Yunhe Wang, Chang Xu, Zhaohui Yang 等ICCV 2019 · 427 次引用
  3. SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and GenerationChongyu Fan, Jiancheng Liu, Yihua Zhang, Eric Wong 等ICLR 2024 · 351 次引用
  4. Fast Machine Unlearning without Retraining through Selective Synaptic DampeningJack Foster, Stefan Schoepf, Alexandra BrintrupAAAI 2024 · 208 次引用
  5. Up to 100x Faster Data-Free Knowledge DistillationGongfan Fang, Kanya Mo, Xinchao Wang, Jie Song 等AAAI 2022 · 103 次引用

相关 Paper

  1. RUAGO: Effective and Practical Retain-Free Unlearning via Adversarial Attack and OOD GeneratorSangyong Lee, Sangjun Chung, Simon S. WooNeurIPS 2025 · 3 次引用
  2. When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You NeedZiming Hong, Runnan Chen, Zengmao Wang, Bo Han 等ICML 2025
  3. Always Be Dreaming: A New Approach for Data-Free Class-Incremental LearningJames Seale Smith, Yen-Chang Hsu, Jonathan C. Balloch, Yilin Shen 等ICCV 2021 · 208 次引用
  4. Remaining-data-free Machine Unlearning by Suppressing Sample ContributionXinwen Cheng, Zhehao Huang, Wenxing Zhou, Zhengbao He 等ICLR 2026 · 11 次引用
  5. Adversarial Mixup UnlearningZhuoyi Peng, Yixuan Tang, Yi YangICLR 2025
黄昏的海面,两侧是细线勾勒的悬崖