Causality-inspired Federated Learning for Dynamic Spatio-Temporal Graphs

• URL: http://arxiv.org/abs/2603.29384v1
• Date: Tue, 31 Mar 2026 07:52:56 GMT
• Title: Causality-inspired Federated Learning for Dynamic Spatio-Temporal Graphs
• Abstract summary: Federated Graph Learning (FGL) has emerged as a powerful paradigm for decentralized training of graph neural networks.<n>Existing FGL methods assume that all features are equally transferable across clients, overlooking the presence of client-specific knowledge in real-world graphs.<n>We propose a novel causality-inspired framework named SC-FSGL, which explicitly decouples transferable causal knowledge from client-specific noise.
• Score: 32.47167190970743
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Structural Entropy-Driven Graph Diffusion Generation for One-Shot Federated Graph Learning [16.26727371966201]
  One-shot federated graph learning (FGL) requires the server to estimate client contributions from highly compressed information.<n>We propose SPIRE, a Structural Entropy-Driven Graph Diffusion Generation method that introduces topology-aware client differentiation into one-shot FGL.
  arXiv  Detail & Related papers  (2026-09-06T09:31:12Z)
• FlatLand: Personalized Graph Federated Learning via Tailored Lorentz Space [54.48585280499489]
  Federated learning enables privacy-preserving collaborative training, but highly heterogeneous client data remain challenging.<n>We propose FlatLand, a novel personalized federated learning method that embeds different clients' data in tailored Lorentz space of hyperbolic geometry.
  arXiv  Detail & Related papers  (2026-08-21T13:42:47Z)
• Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization [56.95448807869383]
  Federated Learning (FL) has emerged as a compelling paradigm for privacy-preserving distributed machine learning.<n>Recent studies find that the gradients exchanged in the FL system are also vulnerable to privacy leakage.<n>We propose textbfGradient textbfInversion over textbfFeature textbfDomains (GIFD)
  arXiv  Detail & Related papers  (2026-04-01T14:32:15Z)
• Rethinking Federated Graph Foundation Models: A Graph-Language Alignment-based Approach [8.517604507672262]
  Recent studies of federated graph foundational models (FedGFMs) break the idealized and untenable assumption of having centralized data storage to train graph foundation models.<n>Existing studies that project aligned generalizable knowledge onto a discrete token space via vector-quantized backbones suffer from irreversible knowledge loss during the quantization process.
  arXiv  Detail & Related papers  (2026-01-29T07:50:00Z)
• Towards Federated Clustering: A Client-wise Private Graph Aggregation Framework [57.04850867402913]
  Federated clustering addresses the challenge of extracting patterns from decentralized, unlabeled data.<n>We propose Structural Privacy-Preserving Federated Graph Clustering (SPP-FGC), a novel algorithm that innovatively leverages local structural graphs as the primary medium for privacy-preserving knowledge sharing.<n>Our framework achieves state-of-the-art performance, improving clustering accuracy by up to 10% (NMI) over federated baselines while maintaining provable privacy guarantees.
  arXiv  Detail & Related papers  (2025-11-14T03:05:22Z)
• Unlocking Dynamic Inter-Client Spatial Dependencies: A Federated Spatio-Temporal Graph Learning Method for Traffic Flow Forecasting [13.035721364418471]
  Federated Spatio-Temporal Graph with Dynamic Inter-Client Dependencies (FedSTGD) is a framework designed to model and reconstruct dynamic inter-client spatial dependencies in federated learning.<n>Experiments on four real-world datasets demonstrate that FedSTGD achieves superior performance over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-11-13T15:57:19Z)
• FedHERO: A Federated Learning Approach for Node Classification Task on Heterophilic Graphs [55.51300642911766]
  Federated Graph Learning (FGL) empowers clients to collaboratively train Graph neural networks (GNNs) in a distributed manner.<n>FGL methods usually require that the graph data owned by all clients is homophilic to ensure similar neighbor distribution patterns of nodes.<n>We propose FedHERO, an FGL framework designed to harness and share insights from heterophilic graphs effectively.
  arXiv  Detail & Related papers  (2025-04-29T22:23:35Z)
• FedGrAINS: Personalized SubGraph Federated Learning with Adaptive Neighbor Sampling [36.314224807189575]
  We propose textitFedGrAINS, a novel data-adaptive and sampling-based regularization method for subgraph FL.<n>We show that the inclusion of textitFedGrAINS as a regularizer consistently improves the FL performance compared to baselines.
  arXiv  Detail & Related papers  (2025-01-22T02:35:20Z)
• FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference [31.796411806840087]
  Federated Graph Learning (pFGL) facilitates the decentralized training of Graph Neural Networks (GNNs) without compromising privacy. Previous pFGL methods incorrectly share non-generic knowledge globally and fail to tailor personalized solutions locally. We propose our pFGL framework FedSSP which Shares generic Spectral knowledge while satisfying graph Preferences.
  arXiv  Detail & Related papers  (2024-10-26T07:09:27Z)
• An Aggregation-Free Federated Learning for Tackling Data Heterogeneity [50.44021981013037]
  Federated Learning (FL) relies on the effectiveness of utilizing knowledge from distributed datasets. Traditional FL methods adopt an aggregate-then-adapt framework, where clients update local models based on a global model aggregated by the server from the previous training round. We introduce FedAF, a novel aggregation-free FL algorithm.
  arXiv  Detail & Related papers  (2024-04-29T05:55:23Z)
• FLASH: Federated Learning Across Simultaneous Heterogeneities [55.0981921695672]
  FLASH(Federated Learning Across Simultaneous Heterogeneities) is a lightweight and flexible client selection algorithm.<n>It outperforms state-of-the-art FL frameworks under extensive sources of Heterogeneities.<n>It achieves substantial and consistent improvements over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-02-13T20:04:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.