Summary of Personalized Federated Learning Based on Feature Fusion, by Wolong Xing et al.
Personalized federated learning based on feature fusion
by Wolong Xing, Zhenkui Shi, Hongyan Peng, Xiantao Hu, Xianxian Li
First submitted to arxiv on: 24 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computer Vision and Pattern Recognition (cs.CV)
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 proposed pFedPM approach in this paper addresses the label distribution skew problem in federated learning, where clients’ data is heterogeneous. To improve the global model’s performance on each client, pFedPM replaces traditional gradient uploading with feature uploading, reducing communication costs and allowing for heterogeneous client models. This method preserves privacy to some extent by utilizing feature representations. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated learning helps keep client data private by training a model without sharing it. But sometimes, the final model isn’t good enough on each individual’s device. To solve this problem, researchers developed pFedPM. Instead of sending gradients (how well the model did), pFedPM sends feature representations (important details from the data). This approach reduces communication costs and lets devices have different models, which helps keep their data private. |
Keywords
* Artificial intelligence * Federated learning
