Summary of Computation and Communication Efficient Lightweighting Vertical Federated Learning, by Heqiang Wang et al.
Computation and Communication Efficient Lightweighting Vertical Federated Learning
by Heqiang Wang, Jieming Bian, Lei Wang
First submitted to arxiv on: 30 Mar 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 The paper explores ways to improve computational and communication efficiency in Federated Learning (FL), specifically for Vertical FL. Existing techniques are not directly applicable due to differences in model structures. The authors introduce Lightweight Vertical Federated Learning (LVFL), which employs separate lightweighting strategies for feature models and feature embeddings to boost efficiencies. A convergence bound is established, accounting for both communication and computational lightweighting ratios. Evaluation on an image classification dataset shows LVFL reduces demands while maintaining robust learning performance. This work addresses gaps in Vertical FL’s efficiency. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making a new way to learn things on many devices at once, called Federated Learning (FL). It’s important because it helps computers talk to each other without sharing all their data. The problem is that this only works for some types of learning. To fix this, the authors created a new method called Lightweight Vertical Federated Learning (LVFL). This makes learning faster and more efficient on devices with limited power or bandwidth. They tested LVFL and showed it can learn quickly and accurately without using too much energy or data. This is important because it helps many devices work together to do things like recognize pictures. |
Keywords
» Artificial intelligence » Federated learning » Image classification
