Journal
2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021)
Volume -, Issue -, Pages 3055-3059Publisher
IEEE
DOI: 10.1109/ICASSP39728.2021.9414903
Keywords
machine learning; federated learning; convex optimization; estimation; complex networks
Categories
Funding
- Academy of Finland [331197]
- Academy of Finland (AKA) [331197] Funding Source: Academy of Finland (AKA)
Ask authors/readers for more resources
This paper presents a novel algorithm for federated learning from large collections of local datasets, utilizing network structure and a networked linear regression model. The algorithm solves a network Lasso problem using a primal-dual method, resulting in a distributed federated learning algorithm. A detailed analysis of the statistical and computational properties of the algorithm is provided.
This paper formulates and studies a novel algorithm for federated learning from large collections of local datasets. This algorithm capitalizes on an intrinsic network structure that relates the local datasets via an undirected empirical graph. We model such big data over networks using a networked linear regression model. Each local dataset has individual regression weights. The weights of close-knit sub-collections of local datasets are enforced to deviate only little. This lends naturally to a network Lasso problem which we solve using a primal-dual method. We obtain a distributed federated learning algorithm via a message passing implementation of this primal-dual method. We provide a detailed analysis of the statistical and computational properties of the resulting federated learning algorithm.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available