Summary of Non-iid Data in Federated Learning: a Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions, by Daniel M. Jimenez G. et al.
Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions
by Daniel M. Jimenez G., David Solans, Mikko Heikkila, Andrea Vitaletti, Nicolas Kourtellis, Aris Anagnostopoulos, Ioannis Chatzigiannakis
First submitted to arxiv on: 19 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 This paper presents a technical survey that aims to provide a comprehensive framework for understanding non-independent and identically distributed (non-IID) data in Federated Learning (FL). The authors highlight the challenge of non-IID data in FL, which can result in poor model performance and slower training times. They propose a detailed taxonomy for classifying and quantifying non-IID data, as well as metrics to measure data heterogeneity. Additionally, the paper describes popular solutions for addressing non-IID data and standardized frameworks used in FL with heterogeneous data. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study looks at how machine learning models can be trained without sharing personal data among users. When this approach doesn’t work because user data isn’t similar, it’s called non-IID data. The authors want to help researchers understand what these problems are and how to fix them. They created a new way of organizing and measuring these issues, which will help make FL better for everyone. |
Keywords
* Artificial intelligence * Federated learning * Machine learning
