Summary of Federated Learning Clients Clustering with Adaptation to Data Drifts, by Minghao Li (1) et al.
Federated Learning Clients Clustering with Adaptation to Data Drifts
by Minghao Li, Dmitrii Avdiukhin, Rana Shahout, Nikita Ivkin, Vladimir Braverman, Minlan Yu
First submitted to arxiv on: 3 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: 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 This paper introduces Fielding, a Federated Learning (FL) framework that addresses data drifts in clustered FL solutions. Federated Learning enables deep learning model training across edge devices while protecting user privacy by retaining raw data locally. However, data heterogeneity in client distributions slows model convergence and leads to plateauing with reduced precision. Fielding detects drifts on all clients and performs selective label distribution-based re-clustering to balance cluster optimality and model performance, remaining robust to malicious clients and varied heterogeneity degrees. The evaluations show that Fielding improves model final accuracy by 1.9%-5.9% and reaches target accuracies 1.16x-2.61x faster. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Fielding is a new way to train deep learning models on many devices at the same time, while keeping user data private. Normally, when training these models, the data from different devices can be very different, which slows down how well the model works. Fielding groups similar devices together and trains separate models for each group. This makes it work better than usual methods. The important thing about Fielding is that it can handle when the data on the devices changes over time, which can make the model not work as well. Fielding does this by looking at all the devices and rearranging the groups to keep them similar. This helps the model be more accurate and faster. |
Keywords
» Artificial intelligence » Clustering » Deep learning » Federated learning » Precision
