Summary of Improving Local Training in Federated Learning Via Temperature Scaling, by Kichang Lee et al.
Improving Local Training in Federated Learning via Temperature Scaling
by Kichang Lee, Songkuk Kim, JeongGil Ko
First submitted to arxiv on: 18 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 This paper proposes a novel approach for federated learning called FLex&Chill, which uses the Logit Chilling method to expedite model convergence and improve inference accuracy in the presence of non-independent and identically distributed (non-i.i.d.) training data. The authors demonstrate that this approach can significantly improve model performance, with up to 6X faster convergence time and up to 3.37% better inference accuracy compared to existing methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated learning is a way for devices to learn together without sharing their data. But when the data is different on each device, it’s hard to get accurate results. This paper suggests a new method called FLex&Chill that helps devices learn faster and better by using something called Logit Chilling. It works well even when the data is different on each device. |
Keywords
* Artificial intelligence * Federated learning * Inference
