Summary of Fedcross: Intertemporal Federated Learning Under Evolutionary Games, by Jianfeng Lu et al.
FedCross: Intertemporal Federated Learning Under Evolutionary Games
by Jianfeng Lu, Ying Zhang, Riheng Jia, Shuqin Cao, Jing Liu, Hao Fu
First submitted to arxiv on: 22 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Distributed, Parallel, and Cluster Computing (cs.DC); 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 The proposed intertemporal incentive framework, FedCross, addresses the challenges posed by dynamic mobile networks with high mobility, intermittent connectivity, and bandwidth limitation in Federated Learning (FL). By migrating interrupted training tasks to feasible mobile devices, FedCross ensures the continuity of FL tasks. The framework consists of two stages: Stage 1 addresses task allocation across regions under resource constraints using a multi-objective migration algorithm, while Stage 2 utilizes a procurement auction mechanism to allocate rewards among base stations and incentivize sustained user participation. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary FedCross helps mobile devices train collaboratively without worrying about their movement. It does this by migrating interrupted training tasks to other devices that are available and have enough resources. This is important because frequent migrations can cause high communication overhead, which slows down the learning process. The framework has two parts: first, it decides which devices should receive which tasks based on how much resource they have left. Then, it uses a special auction system to give rewards to base stations that provide good models and encourage them to keep participating. |
Keywords
» Artificial intelligence » Federated learning
