Summary of Vertical Federated Learning Hybrid Local Pre-training, by Wenguo Li et al.
Vertical Federated Learning Hybrid Local Pre-training
by Wenguo Li, Xinling Guo, Xu Jiao, Tiancheng Huang, Xiaoran Yan, Yao Yang
First submitted to arxiv on: 20 May 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 proposes a novel Vertical Federated Learning (VFL) Hybrid Local Pre-training (VFLHLP) approach, which addresses the limitations of conventional VFL by leveraging unaligned data. The authors demonstrate that their method achieves better performance on real-world advertising datasets compared to baseline methods. The proposed approach pre-trains local networks on local data and then adjusts or enhances sub-models during downstream federated learning. This improves the prediction skills of models in a VFL setting, where enterprises aim to exploit more valuable features from diverse departments. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper solves a problem in Vertical Federated Learning (VFL) by using unaligned data. They make a new model that works better than others on real advertising datasets. The model first trains small networks on each device’s data, and then uses these trained networks to make the main model better. This helps the main model predict things more accurately. |
Keywords
» Artificial intelligence » Federated learning
