Preprint
Federated Learning on Adaptively Weighted Nodes by Bilevel Optimization
ArXiv.org
07/21/2022
DOI: 10.48550/arxiv.2207.10751
Abstract
We propose a federated learning method with weighted nodes in which the
weights can be modified to optimize the model's performance on a separate
validation set. The problem is formulated as a bilevel optimization where the
inner problem is a federated learning problem with weighted nodes and the outer
problem focuses on optimizing the weights based on the validation performance
of the model returned from the inner problem. A communication-efficient
federated optimization algorithm is designed to solve this bilevel optimization
problem. Under an error-bound assumption, we analyze the generalization
performance of the output model and identify scenarios when our method is in
theory superior to training a model only locally and to federated learning with
static and evenly distributed weights.
Details
- Title: Subtitle
- Federated Learning on Adaptively Weighted Nodes by Bilevel Optimization
- Creators
- Yankun HuangQihang LinNick StreetStephen Baek
- Resource Type
- Preprint
- Publication Details
- ArXiv.org
- DOI
- 10.48550/arxiv.2207.10751
- ISSN
- 2331-8422
- Language
- English
- Date posted
- 07/21/2022
- Academic Unit
- Business Analytics; Nursing; Iowa Technology Institute; Computer Science; Bus Admin College; Radiation Oncology
- Record Identifier
- 9984380632202771
Metrics
12 Record Views