Decentralized Federated Learning of Probabilistic Generative Classifiers
This addresses the problem of privacy-preserving model training in decentralized settings for applications like edge computing, but it is incremental as it builds on existing federated learning paradigms with a specific classifier type.
The paper tackles decentralized federated learning by proposing a method for collaboratively learning probabilistic generative classifiers across a network of heterogeneous users without a central server, achieving convergence to a globally competitive model across various network conditions and non-i.i.d. data distributions.
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.