Summary of Communication-efficient Hybrid Federated Learning For E-health with Horizontal and Vertical Data Partitioning, by Chong Yu et al.
Communication-Efficient Hybrid Federated Learning for E-health with Horizontal and Vertical Data Partitioning
by Chong Yu, Shuaiqi Shen, Shiqiang Wang, Kuan Zhang, Hai Zhao
First submitted to arxiv on: 15 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: 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 This paper explores the challenges and opportunities in applying federated learning to e-health, where smart devices and medical institutions collaborate to collect patients’ data for AI-driven diagnosis. The authors highlight two main issues: horizontally partitioned data and vertically partitioned data, which require a combination of Horizontal Federated Learning (HFL) and Vertical Federated Learning (VFL) techniques. However, naive combinations have limitations in terms of training efficiency, convergence analysis, and parameter tuning strategies. To overcome these challenges, the authors propose a hybrid federated learning framework with one intermediate result exchange and two aggregation phases, along with the Hybrid Stochastic Gradient Descent (HSGD) algorithm to train models. The proposed approach achieves communication efficiency while maintaining desired accuracy. Experimental results validate the effectiveness of this approach. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research focuses on how artificial intelligence can help doctors make better diagnoses using data from many devices and medical institutions. Right now, there are challenges in sharing this information because it’s stored differently by each device. The authors want to find a way to share the data efficiently while still getting accurate results. They propose a new method that combines two existing approaches and has special algorithms to adjust how the data is shared. This helps reduce the amount of data being sent between devices, making it faster and more efficient. |
Keywords
» Artificial intelligence » Federated learning » Stochastic gradient descent
