Organizations: School of Information and Communication Engineering, University of Electronic Science and Technology of China, China · Division of Integrative Systems and Design, Hong Kong University of Science and Technology, China · School of Computer Science and Technology, Huazhong University of Science and Technology, China
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.
Figures & tables
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 2: A conceptual illustration inspired by the SCM on client k, showing the relationships among observed variables and latent components.
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.
Client
METRLA
PEMSD4
PEMSD7(M)
PEMSD8
PEMSBAY
Avg.
Metric
MAE
MAPE
MAE
MAPE
MAE
MAPE
MAE
MAPE
MAE
MAPE
MAE
MAPE
FedAvg
12.21
23.58%
3.41
7.13%
5.02
14.25%
3.72
7.22%
3.44
7.69%
5.56
11.97%
FedProx
7.80
19.37%
3.20
6.83%
7.15
16.22%
3.09
6.70%
4.35
10.15%
5.12
11.85%
Moon
7.54
18.00%
2.65
5.57%
6.21
15.66%
3.11
5.84%
4.35
8.11%
4.77
10.64%
FedRep
6.78
17.71%
8.88
14.95%
4.37
12.15%
2.46
5.79%
7.89
13.67%
6.07
12.85%
FedStar
28.71
56.69%
4.35
8.17%
16.41
34.24%
3.25
7.16%
33.71
53.31%
17.29
31.91%
Table 1: Performance comparison of different approaches for FSTG on various datasets (Clients).
Time
60 min
30 min
15 min
Metric
MAE
MAPE
MAE
MAPE
MAE
MAPE
FedAvg
5.56
11.97%
4.80
10.99%
5.32
10.83%
FedProx
5.12
11.85%
4.68
9.85%
4.15
9.04%
Moon
4.77
10.64%
5.12
10.95%
5.31
13.30%
FedRep
6.07
12.85%
3.93
8.48%
4.55
10.83%
FedStar
17.29
31.91%
23.32
42.59%
19.93
35.00%
Table 2: Performance across prediction horizons.
Figure 4: Performance Analysis of SC-FSGL on the PEMSD4 Dataset: (a) Prediction Results, (b) MAE Curves, and (c) t-SNE Visualization of Disentangled Causal Representations.
Figure 5: Ablation Study of SC-FSGL.
Appendix figures & tables6 assets
Supplementary material from the paper’s appendix.
Appendix
Datasets
Nodes
Data Points
Time Steps
PLACE
METRLA
207
7,094,304
34272
Los Angeles
PEMSD4
307
5,216,544
34249
SF Bay Area
PEMSD7(M)
228
2,889,216
16969
California
PEMSD8
170
3,035,520
12649
SB Area
PEMSBAY
325
16,937,700
17833
SF Bay Area
Appendix
Table 1: Here are the specific details for the five datasets, with each client possessing one dataset.
Baseline
URL
FedAvg
https://github.com/katsura-jp/fedavg.pytorch
FedProx
https://github.com/litian96/FedProx
FedRep
https://github.com/lgcollins/FedRep
Moon
https://github.com/QinbinLi/MOON
FedStar
https://github.com/yuetan031/FedStar
MegaCRN
https://github.com/deepkashiwa20/MegaCRN
Appendix
Table 2: Baseline methods and their GitHub links.
Figure 1: Hyper-parameter studies about a and b .
Figure 2: t-SNE Visualization of Representations Across Communication Rounds.
Figure 3: The RMSE and MAPE Curves of SC-FFSGL.
Figure 4: Visualization of Prediction Performance on Heterogeneous Clients.
Spatiotemporal prediction on graph-structured data is central to traffic forecasting and environmental monitoring, yet decentralized and heterogeneous data complicate both sequence modeling and collaborative training. We propose F2STNet, a federated forecasting framework that combines truncated graph-Fourier features, a lightweight diagonal state-space temporal encoder, graph convolution, and Fairness-aware Federated Aggregation (FFA). The spectral branch exposes graph-frequency structure, while the state-space layer models long temporal dependencies with linear complexity in the sequence length. FFA adjusts the FedAvg prior using client validation losses and an increasing fairness schedule. Experiments on PeMS04, HZMetro, and KnowAir show favorable forecasting accuracy relative to the evaluated baselines; federated experiments on PeMS04 additionally improve worst-client and client-dispersion metrics.
Jiayi Zhang, Jinfeng Xu, Hewei Wang +7
University of Nottingham · The University of Hong Kong · Carnegie Mellon University +1
Federated Graph Learning (FGL) is a distributed learning paradigm that enables collaborative training over large-scale subgraphs located on multiple local systems. However, most existing FGL approaches rely on synchronous communication, which leads to inefficiencies and is often impractical in real-world deployments. Meanwhile, current asynchronous federated learning (AFL) methods are primarily designed for conventional tasks such as image classification and natural language processing, consequently failing to account for the unique topological properties of graph data. Directly applying these methods to graph learning frequently results in semantic drift and representational inconsistency within the global model. To address these challenges, we propose FedSA-GCL, a semi-asynchronous federated framework that leverages both inter-client label distribution divergence and graph topological characteristics through a novel ClusterCast mechanism for efficient training. We evaluate FedSA-GCL on multiple real-world graph datasets using the Louvain and Metis algorithms and conduct comparative analysis against 10 baselines. Extensive experiments demonstrate that our method achieves superior robustness and outstanding efficiency, outperforming the baselines by an average margin of 1.9% with Louvain and 3.0% with Metis.
Zhongzheng Yuan, Lianshuai Guo, Xunkai Li +3
Shandong University, School of Airspace Science and Engineering, Weihai 264209, China · Beijing Institute of Technology, School of Computer Science and Technology, Beijing 100081, China · Sun Yat-sen University, School of Computer Science and Engineering, Guangzhou 510275, China
One-shot federated graph learning (FGL) requires the server to estimate client contributions from highly compressed information, yet conventional volume-based weighting captures the amount of client data while overlooking how its connectivity is organized. In this paper, we propose SPIRE, a Structural Entropy-Driven Graph Diffusion Generation method that introduces topology-aware client differentiation into one-shot FGL. Specifically, we employ first-order degree-distribution structural entropy as a compact descriptor of degree-mass dispersion and use it to derive structural client weights, providing an inductive bias that accounts for differences in graph topology beyond data volume. On the generation side, a graph diffusion model on the server synthesizes pseudographs conditioned on the weighted client prototypes, capturing both semantic and structural information without requiring additional client-side training. The generated pseudographs are then assembled via disjoint union fusion to train a global graph neural network. Extensive experiments on seven real-world graph datasets demonstrate that SPIRE consistently outperforms conventional and one-shot FGL methods, with particularly strong gains under highly heterogeneous (non-IID) and graph-perturbed settings.
Shutong Zheng, Lele Fu, Sheng Huang +2
Sun Yat-sen University Guangzhou, China · Nanyang Technological University Singapore