FedDis: A Causal Disentanglement Framework for Federated Traffic Prediction

TL;DR

FedDis introduces a causal disentanglement framework for federated traffic prediction, effectively separating client-specific local dynamics from global patterns to improve performance on decentralized, heterogeneous data.

Contribution

It is the first to apply causal disentanglement in federated spatial-temporal prediction, using a dual-branch architecture with mutual information minimization for effective knowledge transfer.

Findings

Achieves state-of-the-art results on four benchmark datasets

Demonstrates robustness to data heterogeneity

Shows improved adaptability to local environments

Abstract

Federated learning offers a promising paradigm for privacy-preserving traffic prediction, yet its performance is often challenged by the non-identically and independently distributed (non-IID) nature of decentralized traffic data. Existing federated methods frequently struggle with this data heterogeneity, typically entangling globally shared patterns with client-specific local dynamics within a single representation. In this work, we postulate that this heterogeneity stems from the entanglement of two distinct generative sources: client-specific localized dynamics and cross-client global spatial-temporal patterns. Motivated by this perspective, we introduce FedDis, a novel framework that, to the best of our knowledge, is the first to leverage causal disentanglement for federated spatial-temporal prediction. Architecturally, FedDis comprises a dual-branch design wherein a Personalized Bank learns to capture client-specific factors, while a Global Pattern Bank distills common knowledge. This separation enables robust cross-client knowledge transfer while preserving high adaptability to unique local environments. Crucially, a mutual information minimization objective is employed to enforce informational orthogonality between the two branches, thereby ensuring effective disentanglement. Comprehensive experiments conducted on four real-world benchmark datasets demonstrate that FedDis consistently achieves state-of-the-art performance, promising efficiency, and superior expandability.