Summary of Intelligent Agents For Auction-based Federated Learning: a Survey, by Xiaoli Tang et al.
Intelligent Agents for Auction-based Federated Learning: A Survey
by Xiaoli Tang, Han Yu, Xiaoxiao Li, Sarit Kraus
First submitted to arxiv on: 20 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: 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 This survey provides a comprehensive overview of the Intelligent Agents for Auction-based Federated Learning (IA-AFL) literature. It proposes a multi-tiered taxonomy that organizes existing works based on stakeholders served, auction mechanisms adopted, and agent goals. The paper analyzes limitations of existing approaches, summarizes performance evaluation metrics, and discusses promising future directions for stakeholder-oriented decision support in IA-AFL ecosystems. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Auction-based federated learning (AFL) helps people share data to train artificial intelligence models. This type of sharing is important because it allows many people to contribute their data without having to give up control over their information. Intelligent agents are computer programs that can make decisions on our behalf. In the context of AFL, these agents help decide who gets rewarded for contributing their data and how those rewards are distributed. Researchers in this field are trying to understand what types of intelligent agents work best and how they can be used to improve the sharing of data. |
Keywords
» Artificial intelligence » Federated learning
