Summary of Fedquit: On-device Federated Unlearning Via a Quasi-competent Virtual Teacher, by Alessio Mora et al.
FedQUIT: On-Device Federated Unlearning via a Quasi-Competent Virtual Teacher
by Alessio Mora, Lorenzo Valerio, Paolo Bellavista, Andrea Passarella
First submitted to arxiv on: 14 Aug 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 The proposed Federated Learning (FL) algorithm, FedQUIT, addresses the issue of participants exercising their right to be forgotten in collaborative machine learning models. The solution uses knowledge distillation to remove the contribution of forgetting data from the global model while preserving its generalization ability. FedQUIT is efficient, effective, and applicable in both centralized and federated settings, requiring less than 2.5% additional communication rounds to recover generalization performances after unlearning. This approach ensures better privacy guarantees for individuals’ data when machine learning models are collaboratively trained. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated Learning helps keep people’s personal data private by training AI models together. Sometimes, a person might want their old data removed from the model. But current solutions don’t do this well. The new algorithm, FedQUIT, makes it possible to remove this data without hurting the overall performance of the global model. This is good news for keeping our data safe! |
Keywords
» Artificial intelligence » Federated learning » Generalization » Knowledge distillation » Machine learning
