Summary of Federated Learning For Distribution Skewed Data Using Sample Weights, by Hung Nguyen et al.
Federated Learning for distribution skewed data using sample weights
by Hung Nguyen, Peiyuan Wu, Morris Chang
First submitted to arxiv on: 5 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 addresses a significant issue in federated learning, where clients’ data distributions differ from the global distribution, leading to reduced performance. To improve this, the authors propose adjusting client distributions closer to the global distribution using sample weights. This is achieved by leveraging a neural network-based density estimation model, MADE, which allows for density information exchange without exposing raw data. The approach theoretically derives a solution for adjusting skewness and experiments on three real-world datasets show improved accuracy and reduced communication costs. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated learning helps computers learn together without sharing their private data. But this works only if all the data is similar. What happens when some computers have different types of data? This can cause problems, like slower learning or lower accuracy. The authors found a way to fix this by adjusting the data so it’s more similar to the global distribution. They used a special model called MADE that helps exchange information without sharing raw data. Tests on three real-world datasets show their method works better and is faster. |
Keywords
* Artificial intelligence * Density estimation * Federated learning * Neural network
