Summary of Controlling Participation in Federated Learning with Feedback, by Michael Cummins and Guner Dilsad Er and Michael Muehlebach
Controlling Participation in Federated Learning with Feedback
by Michael Cummins, Guner Dilsad Er, Michael Muehlebach
First submitted to arxiv on: 28 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Optimization and Control (math.OC)
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 proposed FedBack method addresses the issue of client participation in federated learning by employing control-theoretic principles in ADMM-based federated learning. This deterministic approach models client participation as a discrete-time dynamical system and adjusts each client’s participation rate individually based on their optimization dynamics using an integral feedback controller. The paper provides global convergence guarantees for FedBack by building on recent federated learning research. Numerically, FedBack achieves up to 50% improvement in communication and computational efficiency over traditional methods that rely on a random selection of clients. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary FedBack is a new way to make machines learn together without sending too much data between them. Right now, machines are chosen at random to help with learning, but this can be slow and wasteful. FedBack fixes this by making each machine’s role clear and adjusting it as needed. This makes the whole process faster and more efficient. The idea works well in practice, cutting down on unnecessary communication and computation. |
Keywords
» Artificial intelligence » Federated learning » Optimization
