Summary of Fedgta: Topology-aware Averaging For Federated Graph Learning, by Xunkai Li et al.
FedGTA: Topology-aware Averaging for Federated Graph Learning
by Xunkai Li, Zhengyu Wu, Wentao Zhang, Yinlin Zhu, Rong-Hua Li, Guoren Wang
First submitted to arxiv on: 22 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Databases (cs.DB); Social and Information Networks (cs.SI)
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 Medium Difficulty summary: Federated Graph Learning (FGL) enables collaborative training on subgraphs across multiple local systems. Existing FGL studies focus on optimizing machine learning models or enhancing performance with complex local models. However, these approaches often neglect graph structure, leading to poor performance and slow convergence. To address this, we propose Federated Graph Topology-aware Aggregation (FedGTA), a personalized optimization strategy that optimizes through topology-aware local smoothing confidence and mixed neighbor features. FedGTA achieves state-of-the-art performance while exhibiting high scalability and efficiency in 12 multi-scale real-world datasets, including the large-scale ogbn-papers100M graph database. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Low Difficulty summary: Imagine you have a big puzzle that you can’t solve on your own. But what if you could work together with friends who also have puzzles to solve? That’s kind of like what Federated Graph Learning does. It helps computers learn from each other by sharing small pieces of information about their puzzles (called graphs). The problem is that most methods don’t take into account the special structure of these graphs, which can lead to poor results. To fix this, we created a new method called FedGTA that uses the graph’s structure to make better decisions. We tested it on many real-world datasets and found that it works really well! |
Keywords
* Artificial intelligence * Machine learning * Optimization
