Summary of Coast: Validation-free Contribution Assessment For Federated Learning Based on Cross-round Valuation, by Hao Wu et al.
CoAst: Validation-Free Contribution Assessment for Federated Learning based on Cross-Round Valuation
by Hao Wu, Likun Zhang, Shucheng Li, Fengyuan Xu, Sheng Zhong
First submitted to arxiv on: 4 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 method called CoAst for assessing the contribution of individual participants in federated learning (FL) without requiring a validation dataset. The authors identify limitations in existing approaches, including the need for representative validation data or relying on a single training round that is susceptible to stochasticity. CoAst addresses these issues by quantizing model parameters and evaluating similarity between local and global updates across multiple communication rounds. Experimental results show that CoAst achieves comparable reliability to validation-based methods while outperforming existing validation-free approaches. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps solve a problem in how people contribute to a big data project called federated learning. Right now, there’s no good way to figure out who is most helping without having extra test data. The authors created a new method called CoAst that can do this job without needing any special test data. They found some old ways of doing this don’t work well because they rely on tricky things like random chance. CoAst is different and seems to work better. |
Keywords
» Artificial intelligence » Federated learning
