Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Causality-inspired Federated Learning for Dynamic Spatio-Temporal Graphs

Yuxuan Liu, Wenchao Xu, Haozhao Wang, Zhiming He, Zhaofeng Shi, Chongyang Xu, Peichao Wang, Boyuan Zhang

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.

Causality-inspired Federated Learning for Dynamic Spatio-Temporal Graphs

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.

Paper Structure

This paper contains 38 sections, 1 theorem, 34 equations, 9 figures, 4 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Causal Representation Learning in GNNs
  4. Spatio-temporal Graph Learning
  5. Federated Graph Learning on STGs
  6. Problem Description
  7. Problem setting & notations
  8. Causal View of FSTGs
  9. Methodology
  10. Spatio-Temporal Embedding ($STE$)
  11. Conditional Separation Module
  12. Causal Codebook
  13. Local Training and Inference
  14. Convergence Analysis
  15. Experiments
  16. ...and 23 more sections

Key Result

Theorem 1

causal codebook converges to the following bound when the learning rate is $\eta$,

Figures (9)

  • Figure 1: Spatial and temporal heterogeneity across clients and shared causal patterns. (a) differences in graph structures (nodes and edges). (b) variation in traffic trends at the same time. (c) similar road layouts imply shared spatial causal structures. (d) recurrent temporal patterns suggest shared temporal causality.
  • Figure 1: Hyper-parameter studies about $a$ and $b$.
  • Figure 2: A conceptual illustration inspired by the SCM on client k, showing the relationships among observed variables and latent components.
  • Figure 2: t-SNE Visualization of Representations Across Communication Rounds.
  • Figure 3: The figure illustrates the overall architecture of SC-FSGL, including the client-side feature extraction, causal codebook construction, and global aggregation process. The model extracts spatio-temporal features, separates shared and client-specific causal variables, and leverages the causal codebook to enhance the prediction accuracy through soft intervention and contrastive representation alignment.
  • ...and 4 more figures

Theorems & Definitions (1)

  • Theorem 1