Topology Learning for Heterogeneous Decentralized Federated Learning over Unreliable D2D Networks
This addresses convergence issues in decentralized federated learning for mobile devices in unreliable networks, but it is incremental as it builds on existing DFL frameworks.
The paper tackles the challenges of data heterogeneity and unreliable communication in decentralized federated learning over D2D networks, proposing a topology learning method (ToLRDUL) that improves convergence speed and test accuracy, as validated by experiments.
With the proliferation of intelligent mobile devices in wireless device-to-device (D2D) networks, decentralized federated learning (DFL) has attracted significant interest. Compared to centralized federated learning (CFL), DFL mitigates the risk of central server failures due to communication bottlenecks. However, DFL faces several challenges, such as the severe heterogeneity of data distributions in diverse environments, and the transmission outages and package errors caused by the adoption of the User Datagram Protocol (UDP) in D2D networks. These challenges often degrade the convergence of training DFL models. To address these challenges, we conduct a thorough theoretical convergence analysis for DFL and derive a convergence bound. By defining a novel quantity named unreliable links-aware neighborhood discrepancy in this convergence bound, we formulate a tractable optimization objective, and develop a novel Topology Learning method considering the Representation Discrepancy and Unreliable Links in DFL, named ToLRDUL. Intensive experiments under both feature skew and label skew settings have validated the effectiveness of our proposed method, demonstrating improved convergence speed and test accuracy, consistent with our theoretical findings.