FLAg-SwaP: Distributed Federated Learning Aggregation using Particle Swarm-based Placement

Federated learning has become a promising distributed learning concept with increased assurance of data privacy. Extensive studies on various models of Federated learning have been done since the coinage of its term. One of the important derivatives of federated learning is hierarchical semi-decentralized federated learning, which distributes the load of the aggregation task over multiple nodes and parallelizes the aggregation workload at the breadth of each level of the hierarchy. Various methods have also been proposed to perform inter-cluster and intra-cluster aggregation optimally. Most of the solutions nonetheless, require monitoring the nodes' performance and resource consumption at each round, which necessitates frequently exchanging systematic data. To optimally perform distributed aggregation in semi-decentralized federated learning with minimal reliance on systematic data, we propose Flag-Swap, a Particle Swarm Optimization (PSO) method that optimizes the aggregation placement according only to the processing delay. We propose using sigmoidal decay and growth functions for the cognitive coefficient c 1 and social coefficient c 2 to achieve stable convergence to a minimum total processing delay. Our simulation results show that PSO-based placement can find the optimal placement relatively fast and achieve stable convergence regardless of the resource distribution model, even in scenarios with many clients as candidates for aggregation. Our real-world docker-based implementation of Flag-Swap over the recently emerged FL framework shows superior performance compared to black-box-based deterministic placement strategies, with about 43 minutes faster than random placement, and 32 minutes faster than uniform placement, in terms of total processing time.