Summary of Federated Learning For Data Market: Shapley-ucb For Seller Selection and Incentives, by Kongyang Chen et al.
Federated Learning for Data Market: Shapley-UCB for Seller Selection and Incentives
by Kongyang Chen, Zeming Xu
First submitted to arxiv on: 10 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computer Science and Game Theory (cs.GT)
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 A novel transaction framework for the data trading market has been proposed, addressing information asymmetry between agents and sellers. The framework, based on federated learning architecture, ensures privacy protection while promoting fair compensation to sellers. A seller selection algorithm and incentive mechanism are designed to evaluate seller contributions using gradient similarity and Shapley algorithm, and select the best sellers using modified UCB algorithm. Fair compensation is then made according to each seller’s participation in the training process. The framework’s effectiveness is demonstrated through reasonable experiments, proving its rationality. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine a market where people trade data with each other. There’s an issue where one side has more information than the other, making it hard for both parties to make fair deals. To fix this, researchers have created a new system that uses “federated learning” to protect privacy and ensure sellers get paid fairly. This system chooses the best sellers based on how well they contribute to the data and pays them accordingly. The team tested their idea and showed it works well. |
Keywords
» Artificial intelligence » Federated learning
