Summary of Technical Report: on the Convergence Of Gossip Learning in the Presence Of Node Inaccessibility, by Tian Liu et al.
Technical Report: On the Convergence of Gossip Learning in the Presence of Node Inaccessibility
by Tian Liu, Yue Cui, Xueyang Hu, Yecheng Xu, Bo Liu
First submitted to arxiv on: 17 Jan 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 presents a study on gossip learning (GL), a decentralized alternative to federated learning (FL) that is more suitable for resource-constrained wireless networks, such as Flying Ad-Hoc Networks (FANETs) formed by unmanned aerial vehicles (UAVs). GL can significantly enhance the efficiency and extend the battery life of UAV networks. The paper investigates how data distribution, communication speed, and network connectivity affect the convergence of GL, decomposing weight divergence based on node accessibility. The authors theoretically provide insights into how the number of inaccessible nodes, data non-i.i.d.-ness, and duration of inaccessibility impact convergence. Extensive experiments verify the correctness of findings. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Gossip learning is a new way for drones to share information without needing to be connected all the time. This makes it useful for situations where the drones are flying around and can’t always talk to each other. The problem is that we don’t know exactly how this works when some drones are missing or having trouble communicating. This paper tries to figure out how many missing drones, how different the data is, and how long they’re missing affects how well the gossip learning works. |
Keywords
* Artificial intelligence * Federated learning
