A Decision Model for Federated Learning Architecture Pattern Selection

Abstract

Federated learning is growing fast in both academia and industry to resolve data hungriness and privacy issues in machine learning. A federated learning system being widely distributed with different components and stakeholders requires software system design thinking. For instance, multiple patterns and tactics have been summarised by researchers that cover various aspects, from client management, training configuration, model deployment, etc. However, the multitude of patterns leaves the designers confused about when and which pattern to adopt or adapt. Therefore, in this paper, we present a set of decision models to assist designers and architects who have limited knowledge in federated learning, in selecting architectural patterns for federated learning architecture design. Each decision model maps functional and non-functional requirements of federated learning systems to a set of patterns. we also clarify the trade-offs that may be implicit in the patterns. We evaluated the decision model through a set of interviews with practitioners to assess the correctness and usefulness in guiding the architecture design process through various design decision options.