Summary of Fedprok: Trustworthy Federated Class-incremental Learning Via Prototypical Feature Knowledge Transfer, by Xin Gao et al.
FedProK: Trustworthy Federated Class-Incremental Learning via Prototypical Feature Knowledge Transfer
by Xin Gao, Xin Yang, Hao Yu, Yan Kang, Tianrui Li
First submitted to arxiv on: 4 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE)
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 Federated Class-Incremental Learning (FCIL) method aims to improve continual learning by addressing catastrophic forgetting and data heterogeneity among clients. The authors introduce FedProK, a novel approach that leverages prototypical feature representation for spatial-temporal knowledge transfer. This is achieved through two components: client-side feature translation and server-side prototypical knowledge fusion. Experimental results in both synchronous and asynchronous settings demonstrate the effectiveness of FedProK in selectively transferring spatial-temporal knowledge, outperforming state-of-the-art methods in three aspects of trustworthiness. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary FedProK is a new way to learn new classes while keeping what we already know. This helps when we’re working together with many devices and want to avoid forgetting important information. The approach uses special “prototypical” features that represent knowledge, which are transferred between devices in a way that considers both space (what’s happening on each device) and time (how things change over time). In tests, this method did better than others at three important aspects: being trustworthy, using less data, and preserving privacy. |
Keywords
» Artificial intelligence » Continual learning » Translation
