Summary of Fed-credit: Robust Federated Learning with Credibility Management, by Jiayan Chen et al.
Fed-Credit: Robust Federated Learning with Credibility Management
by Jiayan Chen, Zhirong Qian, Tianhui Meng, Xitong Gao, Tian Wang, Weijia Jia
First submitted to arxiv on: 20 May 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 proposes a novel Federated Learning (FL) approach called Fed-Credit that prioritizes privacy preservation by incorporating credibility management to mitigate potential security risks from malicious devices. Unlike existing solutions, Fed-Credit does not require prior knowledge of the number of attackers or data distribution and instead relies on a credibility set that weighs client contributions based on model similarity. The algorithm incorporates time decay and attitudinal value factors to dynamically adjust reputation weights, achieving a computational complexity of O(n). Experimental results demonstrate superior accuracy and resilience against adversarial attacks on MNIST and CIFAR-10 datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper creates a new way for computers to learn together without sharing private information. It’s like a team effort where each computer contributes its own knowledge, but only shares how good or bad it is at using that knowledge. This helps protect privacy and keeps the learning process fair. The team tested their method on two popular datasets and found that it performed better than other methods in some cases. |
Keywords
» Artificial intelligence » Federated learning
