Summary of Fedcap: Robust Federated Learning Via Customized Aggregation and Personalization, by Youpeng Li et al.
FedCAP: Robust Federated Learning via Customized Aggregation and Personalization
by Youpeng Li, Xinda Wang, Fuxun Yu, Lichao Sun, Wenbin Zhang, Xuyu Wang
First submitted to arxiv on: 16 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
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 Federated learning (FL) is an emerging machine learning paradigm that enables privacy-preserving distributed training. However, FL faces challenges such as data heterogeneity and Byzantine attacks. To address these issues, this paper proposes FedCAP, a robust FL framework that incorporates model update calibration to capture differences in client updates and customized model aggregation to accelerate malicious client detection. Additionally, the framework includes anomaly detection using Euclidean norm-based mechanisms. The authors conduct extensive experiments comparing state-of-the-art baselines, demonstrating FedCAP’s performance in non-IID settings and robustness against poisoning attacks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine if many people could work together to make a machine learning model without sharing their own data. This is called federated learning. But there are challenges: the data might be very different from one person to another, and some people might try to mess with the system. To solve these problems, this paper proposes a new way of doing federated learning called FedCAP. It helps the model update process by calibrating differences between people’s updates, and it can quickly identify and remove malicious users. The authors tested FedCAP and found that it works well even when the data is different or there are attacks. |
Keywords
» Artificial intelligence » Anomaly detection » Federated learning » Machine learning
