Summary of Unlearning During Learning: An Efficient Federated Machine Unlearning Method, by Hanlin Gu et al.
Unlearning during Learning: An Efficient Federated Machine Unlearning Method
by Hanlin Gu, Gongxi Zhu, Jie Zhang, Xinyuan Zhao, Yuxing Han, Lixin Fan, Qiang Yang
First submitted to arxiv on: 24 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Distributed, Parallel, and Cluster Computing (cs.DC)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
Summary difficulty | Written by | Summary |
---|---|---|
High | Paper authors | High Difficulty Summary Read the original abstract here |
Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a new framework for federated machine unlearning (FMU) called FedAU, which addresses limitations in current FMU approaches by incorporating a lightweight auxiliary unlearning module into the learning process. This approach eliminates the need for additional time-consuming steps and enables concurrent unlearning tasks across multiple clients at various levels of granularity. The proposed method is evaluated on MNIST, CIFAR10, and CIFAR100 datasets, demonstrating effective unlearning with preserved model accuracy. |
Low | GrooveSquid.com (original content) | Low Difficulty Summary In a nutshell, this paper introduces a new way to “forget” unwanted data in distributed machine learning systems. It’s called federated machine unlearning (FMU), and the authors propose a solution called FedAU that makes it faster and more efficient. They tested it on some popular datasets and showed that it works well. |
Keywords
» Artificial intelligence » Machine learning