Better Methods and Theory for Federated Learning: Compression, Client Selection and Heterogeneity
This work tackles key issues in federated learning to improve its efficiency and applicability, though it appears incremental as it builds on existing paradigms.
The thesis addresses specific optimization challenges in federated learning, such as compression, client selection, and heterogeneity, by proposing new methods and algorithms with mathematically rigorous guarantees to enable practical solutions.
Federated learning (FL) is an emerging machine learning paradigm involving multiple clients, e.g., mobile phone devices, with an incentive to collaborate in solving a machine learning problem coordinated by a central server. FL was proposed in 2016 by Konečný et al. and McMahan et al. as a viable privacy-preserving alternative to traditional centralized machine learning since, by construction, the training data points are decentralized and never transferred by the clients to a central server. Therefore, to a certain degree, FL mitigates the privacy risks associated with centralized data collection. Unfortunately, optimization for FL faces several specific issues that centralized optimization usually does not need to handle. In this thesis, we identify several of these challenges and propose new methods and algorithms to address them, with the ultimate goal of enabling practical FL solutions supported with mathematically rigorous guarantees.