Summary of Fast-fedul: a Training-free Federated Unlearning with Provable Skew Resilience, by Thanh Trung Huynh et al.
Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience
by Thanh Trung Huynh, Trong Bang Nguyen, Phi Le Nguyen, Thanh Tam Nguyen, Matthias Weidlich, Quoc Viet Hung Nguyen, Karl Aberer
First submitted to arxiv on: 28 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); Emerging Technologies (cs.ET)
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 In this paper, researchers propose a novel unlearning method for federated learning (FL) called Fast-FedUL. The goal is to remove specific training data from trained FL models while preserving knowledge gained from other clients. This approach addresses the challenges of retraining and theoretical assurances in existing unlearning solutions for FL. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper presents a tailored algorithm that eliminates the need for retraining, analyzing the target client’s influence on the global model in each round to systematically remove its impact. Experimental results show that Fast-FedUL effectively removes almost all traces of the target client while retaining knowledge from other clients, achieving high accuracy (up to 98%) on the main task. Moreover, Fast-FedUL has a lower time complexity than retraining, providing a speed 1000 times faster. |
Keywords
* Artificial intelligence * Federated learning
