Summary of Tablepuppet: a Generic Framework For Relational Federated Learning, by Lijie Xu et al.
TablePuppet: A Generic Framework for Relational Federated Learning
by Lijie Xu, Chulin Xie, Yiran Guo, Gustavo Alonso, Bo Li, Guoliang Li, Wei Wang, Wentao Wu, Ce Zhang
First submitted to arxiv on: 23 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Databases (cs.DB); Distributed, Parallel, and Cluster Computing (cs.DC)
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 paper explores whether federated learning (FL) can be applied directly to distributed relational tables across databases, rather than treating them as a single table divided among participants. Current approaches view decentralized training data as a single table, but this is inadequate for handling the intricate SQL operations required to obtain the training data in this scenario. The authors aim to address this limitation by developing a new approach that can handle distributed relational tables. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper tries to find an answer to whether we can directly use federated learning on different relational databases from various places, like banks or hospitals. Right now, we just see these databases as one big table, but in real life, they’re complicated and have lots of relationships between them. The question is: can we make a machine learning system that can learn from all these different databases at the same time? |
Keywords
* Artificial intelligence * Federated learning * Machine learning
