Summary of Federated Multi-task Learning on Non-iid Data Silos: An Experimental Study, by Yuwen Yang et al.
Federated Multi-Task Learning on Non-IID Data Silos: An Experimental Study
by Yuwen Yang, Yuxiang Lu, Suizhi Huang, Shalayiding Sirejiding, Hongtao Lu, Yue Ding
First submitted to arxiv on: 20 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR); 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 Federated Multi-Task Learning (FMTL) approach combines the benefits of Federated Learning and Multi-Task Learning, allowing for collaborative model training on multi-task learning datasets. However, a comprehensive evaluation method that integrates the unique features of both FL and MTL is currently absent in the field. This paper introduces a novel framework, FMTL-Bench, which provides a systematic evaluation of the FMTL paradigm. The benchmark covers various aspects at the data, model, and optimization algorithm levels, with seven sets of comparative experiments that encapsulate a wide array of non-independent and identically distributed (Non-IID) data partitioning scenarios. The framework proposes a systematic process for comparing baselines of diverse indicators, and conducts a case study on communication expenditure, time, and energy consumption. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper introduces Federated Multi-Task Learning (FMTL), which combines the benefits of Federated Learning and Multi-Task Learning to train models on multiple tasks. The FMTL-Bench framework provides a way to evaluate this new approach. It includes several experiments that compare different methods for training FMTL models, including how well they perform in different situations. |
Keywords
* Artificial intelligence * Federated learning * Multi task * Optimization
