Summary of Understanding Server-assisted Federated Learning in the Presence Of Incomplete Client Participation, by Haibo Yang et al.
Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client Participation
by Haibo Yang, Peiwen Qiu, Prashant Khanduri, Minghong Fang, Jia Liu
First submitted to arxiv on: 4 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 The proposed paper investigates server-assisted federated learning (SA-FL) as a solution to mitigate the impacts of incomplete client participation in federated learning (FL). Conventional FL assumes ideal client participation, but in practice, some clients may never participate. SA-FL has been empirically shown to be effective, but lacks theoretical understanding. The authors rigorously investigate SA-FL and show that conventional FL is not PAC-learnable under incomplete client participation, but SA-FL can revive this learnability. They propose the SAFARI algorithm with convergence guarantee, outperforming classic FL in experiments. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated learning (FL) helps machines learn together without sharing data. Sometimes, some computers may not participate in the learning process. Researchers have developed a way to help these computers join in, called server-assisted federated learning (SA-FL). This method uses an auxiliary dataset on the server computer. The authors want to understand how SA-FL works and why it’s effective. They found that traditional FL can’t learn when some computers don’t participate, but SA-FL can. They also created a new algorithm called SAFARI, which helps improve performance. |
Keywords
» Artificial intelligence » Federated learning
