Efficient Collaborations through Weight-Driven Coalition Dynamics in Federated Learning Systems
This addresses communication bottlenecks in federated learning for IoT applications, though it appears incremental as it builds on existing weight-based methods.
The paper tackles the problem of inefficient collaborations in federated learning for IoT systems by forming coalitions based on Euclidean distance between device model weights, with results showing improved structure and communication efficiency compared to traditional averaging algorithms.
In the era of the Internet of Things (IoT), decentralized paradigms for machine learning are gaining prominence. In this paper, we introduce a federated learning model that capitalizes on the Euclidean distance between device model weights to assess their similarity and disparity. This is foundational for our system, directing the formation of coalitions among devices based on the closeness of their model weights. Furthermore, the concept of a barycenter, representing the average of model weights, helps in the aggregation of updates from multiple devices. We evaluate our approach using homogeneous and heterogeneous data distribution, comparing it against traditional federated learning averaging algorithm. Numerical results demonstrate its potential in offering structured, outperformed and communication-efficient model for IoT-based machine learning.