Self-simulation and Meta-Model Aggregation Based Heterogeneous Graph Coupled Federated Learning

• Published in: IEEE internet of things journal p. 1
• Main Authors: Yan, Caihong, Lu, Xiaofeng, Lio, Pietro, Hui, Pan, He, Daojing
• Format: Journal Article
• Language: English
• Published: IEEE 24.09.2024
• Subjects: Analytical models; Coupled Heterogeneous Graphs; Couplings; Data models; Federated learning; Graph neural networks; Heterogeneous Model Aggregation; Internet of Things; Missing Graph Completion; Semantics
• ISSN: 2327-4662; 2327-4662
• DOI: 10.1109/JIOT.2024.3462724

A heterogeneous information network (heterogeneous graph) federated learning plays a crucial role in enabling multi-party collaboration in the IoT system. However, due to differences in business and data, the local models of each participant are heterogeneous and unable to achieve federated aggregation. Furthermore, the non-independent and identically distributed (non-IID) coupling topology structure among participants severely impacts the performance of federated learning. Given the lack of appropriate solutions to these issues, this study proposes a novel heterogeneous graph federated learning framework (HGFL+) based on self-simulation and meta-model aggregation, which includes the following two innovative techniques: (1) The missing coupling supplement module simulates new neighbor nodes on its original heterogeneous graph, and constructs associated edges using multiple encoder-decoder structures, thereby achieving the supplement of missing neighbors with better results than external generative methods. (2) The heterogeneous model aggregation algorithm realizes the fusion of multi-party heterogeneous graph information through mapping, splitting, aggregating, and recombining multiple stages based on the meta-model (the largest basic model unit among participants). We theoretically analyzed the applicability and effectiveness of HGFL+, demonstrating the generalization boundary of HGFL+. Meanwhile, multi-dimensional empirical verification of classification performance, convergence effect, time overhead, model size, and application extension (model, task, domain) validates the effectiveness of the proposed method.