Bandit-based Communication-Efficient Client Selection Strategies for Federated Learning

December 14, 2020 ยท Declared Dead ยท ๐Ÿ› Asilomar Conference on Signals, Systems and Computers

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Yae Jee Cho, Samarth Gupta, Gauri Joshi, Osman YaฤŸan arXiv ID 2012.08009 Category cs.LG: Machine Learning Cross-listed cs.AI Citations 81 Venue Asilomar Conference on Signals, Systems and Computers Last Checked 5 months ago
Abstract
Due to communication constraints and intermittent client availability in federated learning, only a subset of clients can participate in each training round. While most prior works assume uniform and unbiased client selection, recent work on biased client selection has shown that selecting clients with higher local losses can improve error convergence speed. However, previously proposed biased selection strategies either require additional communication cost for evaluating the exact local loss or utilize stale local loss, which can even make the model diverge. In this paper, we present a bandit-based communication-efficient client selection strategy UCB-CS that achieves faster convergence with lower communication overhead. We also demonstrate how client selection can be used to improve fairness.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning

Died the same way โ€” ๐Ÿ‘ป Ghosted