Causality-inspired Federated Learning for Dynamic Spatio-Temporal Graphs

TL;DR

This paper introduces SC-FSGL, a causality-inspired federated learning framework for dynamic spatio-temporal graphs that disentangles invariant causal factors from client-specific noise, improving generalization.

Contribution

The paper proposes a novel causality-inspired framework with a Conditional Separation Module and Causal Codebook to enhance federated learning on dynamic spatio-temporal graphs.

Findings

SC-FSGL outperforms state-of-the-art methods on five heterogeneity STG datasets.

The framework effectively disentangles causal knowledge from client-specific noise.

Representation-level interventions improve cross-client knowledge sharing.

Abstract

Federated Graph Learning (FGL) has emerged as a powerful paradigm for decentralized training of graph neural networks while preserving data privacy. However, existing FGL methods are predominantly designed for static graphs and rely on parameter averaging or distribution alignment, which implicitly assume that all features are equally transferable across clients, overlooking both the spatial and temporal heterogeneity and the presence of client-specific knowledge in real-world graphs. In this work, we identify that such assumptions create a vicious cycle of spurious representation entanglement, client-specific interference, and negative transfer, degrading generalization performance in Federated Learning over Dynamic Spatio-Temporal Graphs (FSTG). To address this issue, we propose a novel causality-inspired framework named SC-FSGL, which explicitly decouples transferable causal knowledge from client-specific noise through representation-level interventions. Specifically, we introduce a Conditional Separation Module that simulates soft interventions through client conditioned masks, enabling the disentanglement of invariant spatio-temporal causal factors from spurious signals and mitigating representation entanglement caused by client heterogeneity. In addition, we propose a Causal Codebook that clusters causal prototypes and aligns local representations via contrastive learning, promoting cross-client consistency and facilitating knowledge sharing across diverse spatio-temporal patterns. Experiments on five diverse heterogeneity Spatio-Temporal Graph (STG) datasets show that SC-FSGL outperforms state-of-the-art methods.