In recent years, Federated Learning (FL) has gained relevance in training collaborative
models without sharing sensitive data. Since its birth, Centralized FL (CFL) has been the …

The problem of Byzantine resilience in distributed machine learning, aka Byzantine machine
learning, consists of designing distributed algorithms that can train an accurate model …

This paper studies the algorithmic stability and generalizability of decentralized stochastic
gradient descent (D-SGD). We prove that the consensus model learned by D-SGD is …

Decentralized federated learning is a training approach that prioritizes user data privacy
protection, while also offering improved scalability and robustness. However, as the number …

One of the key challenges in decentralized and federated learning is to design algorithms
that efficiently deal with highly heterogeneous data distributions across agents. In this paper …

Federated learning (FL) is a pivotal catalyst for enabling large-scale privacy-preserving
distributed machine learning (ML). By eliminating the need for local raw dataset sharing, FL …

Decentralized learning has emerged as an alternative method to the popular parameter-
server framework which suffers from high communication burden, single-point failure and …

Decentralized learning is widely employed for collaboratively training models using
distributed data over wireless networks. Existing decentralized learning methods primarily …

Federated Learning (FL) has been becoming a popular interdisciplinary research area in
both applied mathematics and information sciences. Mathematically, FL aims to …

We study how to train personalized models for different tasks on decentralized devices with
limited local data. We propose" Structured Cooperative Learning (SCooL)", in which a …