Decentralized Federated Learning of Probabilistic Generative Classifiers

TL;DR

This paper introduces a decentralized federated learning method for probabilistic generative classifiers, enabling collaborative model training across networked nodes without a central server, and demonstrates its effectiveness across various settings.

Contribution

It proposes a novel decentralized approach for learning probabilistic classifiers through local statistics sharing, without relying on a central coordinating server.

Findings

Algorithm converges to a globally competitive model

Effective across diverse network topologies and sizes

Handles extreme non-i.i.d. data distributions

Abstract

Federated learning is a paradigm of increasing relevance in real world applications, aimed at building a global model across a network of heterogeneous users without requiring the sharing of private data. We focus on model learning over decentralized architectures, where users collaborate directly to update the global model without relying on a central server. In this context, the current paper proposes a novel approach to collaboratively learn probabilistic generative classifiers with a parametric form. The framework is composed by a communication network over a set of local nodes, each of one having its own local data, and a local updating rule. The proposal involves sharing local statistics with neighboring nodes, where each node aggregates the neighbors' information and iteratively learns its own local classifier, which progressively converges to a global model. Extensive experiments demonstrate that the algorithm consistently converges to a globally competitive model across a wide range of network topologies, network sizes, local dataset sizes, and extreme non-i.i.d. data distributions.