Coordination-free Decentralised Federated Learning on Complex Networks: Overcoming Heterogeneity
This work addresses the challenge of scalable and robust federated learning for edge computing applications where central coordination is unreliable, though it appears incremental as it builds on existing decentralized approaches.
The paper tackles the problem of federated learning in decentralized edge scenarios without a central coordinator, where data and device heterogeneity and complex network structures pose challenges. The proposed decentralized federated learning algorithm enables devices to train accurate models by communicating only with neighbors, achieving better generalization and higher communication efficiency compared to existing methods.
Federated Learning (FL) is a well-known framework for successfully performing a learning task in an edge computing scenario where the devices involved have limited resources and incomplete data representation. The basic assumption of FL is that the devices communicate directly or indirectly with a parameter server that centrally coordinates the whole process, overcoming several challenges associated with it. However, in highly pervasive edge scenarios, the presence of a central controller that oversees the process cannot always be guaranteed, and the interactions (i.e., the connectivity graph) between devices might not be predetermined, resulting in a complex network structure. Moreover, the heterogeneity of data and devices further complicates the learning process. This poses new challenges from a learning standpoint that we address by proposing a communication-efficient Decentralised Federated Learning (DFL) algorithm able to cope with them. Our solution allows devices communicating only with their direct neighbours to train an accurate model, overcoming the heterogeneity induced by data and different training histories. Our results show that the resulting local models generalise better than those trained with competing approaches, and do so in a more communication-efficient way.