Summary of Dual-criterion Model Aggregation in Federated Learning: Balancing Data Quantity and Quality, by Haizhou Zhang et al.
Dual-Criterion Model Aggregation in Federated Learning: Balancing Data Quantity and Quality
by Haizhou Zhang, Xianjia Yu, Tomi Westerlund
First submitted to arxiv on: 12 Nov 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 paper proposes an innovative approach to federated learning (FL), addressing the limitations of existing average aggregation algorithms. By recognizing that not all client-trained data is created equal, the proposed method aims to enhance the efficacy and security of FL systems. The authors acknowledge that current approaches either assume uniform value or solely rely on quantity, neglecting the inherent heterogeneity between clients’ data and the complexities of variations at the aggregation stage. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In simple terms, this paper tries to improve how we share machine learning models with other devices without sharing their private data. They want to make sure that all devices contribute equally and aren’t ignored because they have different types of data or less data overall. |
Keywords
* Artificial intelligence * Federated learning * Machine learning
