Summary of Uncertainty-based Extensible Codebook For Discrete Federated Learning in Heterogeneous Data Silos, by Tianyi Zhang et al.
Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data Silos
by Tianyi Zhang, Yu Cao, Dianbo Liu
First submitted to arxiv on: 29 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 Uncertainty-Based Extensible-Codebook Federated Learning (UEFL) framework addresses the heterogeneity of data across different silos in federated learning (FL). By dynamically mapping latent features to trainable discrete vectors, assessing uncertainty, and extending the discretization dictionary or codebook for high-uncertainty silos, UEFL simultaneously enhances accuracy and reduces uncertainty. Experiments on five datasets show significant improvements in accuracy (3%-22.1%) and uncertainty reduction (38.83%-96.24%), outperforming contemporary state-of-the-art methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated learning is a way to use data from many different sources together, but it can be tricky when the data is very different. The new framework called UEFL helps solve this problem by making sure the model is good at guessing what’s in the new data even if it’s very different from what it saw before. This makes the model more accurate and less uncertain. |
Keywords
* Artificial intelligence * Federated learning
