Structure-Guided Spatiotemporal Attention Graph Neural Network for Traffic Flow Prediction

• URL: http://arxiv.org/abs/2608.14177v1
• Date: Fri, 14 Aug 2026 10:46:37 GMT
• Title: Structure-Guided Spatiotemporal Attention Graph Neural Network for Traffic Flow Prediction
• Abstract summary: This paper proposes the Structure-Guided Stemporal Attention Graph Neural Network (SGSAN) for traffic prediction.<n>We show that SGSAN achieves state-of-the-art predictive accuracy while providing built-in interpretability that organically aligns with traffic network logic.
• Score: 10.55782327097476
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep spatiotemporal models integrating graph convolutions and attention mechanisms have demonstrated excellent performance in network-level traffic flow prediction, owing to their exceptional ability to capture complex spatiotemporal dependencies. Despite their predictive success, deployment of such models in safety-critical urban systems remains constrained by their inherent lack of transparency. Existing post-hoc diagnostic methods often struggle with spurious correlations and fail to unveil the intrinsic decision-making mechanisms governing traffic dynamics, resulting in suboptimal interpretability and limited operational trustworthiness. To address these challenges, this paper proposes the Structure-Guided Spatiotemporal Attention Graph Neural Network (SGSAN). Departing from traditional architectures that rely on unconstrained adaptive graphs, SGSAN explicitly learns a static Directed Dependency Graph (DDG) to identify the invariant macroscopic propagation paths of traffic states. We further introduce an InfoNCE-based soft-coupling mechanism that anchors the model's dynamic spatiotemporal attention to this structural prior, offering a mechanistic account of the model's decision-making process while ensuring robust forecasting by aligning attention-based reasoning with identified macroscopic dependencies and preventing over-reliance on ephemeral local noise. Furthermore, a decoupled two-stage optimization framework is developed to resolve the fundamental conflict between structural discovery and predictive error minimization. Extensive experiments on multiple real-world datasets demonstrate that SGSAN achieves state-of-the-art predictive accuracy while providing built-in interpretability that organically aligns with the physical logic of traffic networks.

Related papers

• GUIDED Network-Agnostic Feature Initialization for Spatial Transferability in GNN-based Models [46.28228608289378]
  The Traffic Assignment Problem is a fundamental but computationally expensive component of transportation planning.<n>This research proposes a network-agnostic initialization layer, termed Geometrically Unconstrained Inductive Demand EmbeDding.<n>This framework standardizes the input space regardless of network scale.<n>It provides a versatile blueprint for generalized origin-destination spatial problems, such as freight logistics and multimodal network optimization.
  arXiv  Detail & Related papers  (2026-07-21T16:41:59Z)
• Timestamp-Aware Spatio-Temporal Graph Contrastive Learning for Network Intrusion Detection [12.117106433382437]
  We propose a novel self-supervised graph neural network (GNN)-based framework for intrusion detection systems.<n>The proposed model explicitly leverage real timestamps, which provides faithful temporal dependencies for representation learning.<n>We show that our method significantly outperforms existing self-supervised approaches and achieves performance comparable to the supervised state-of-the-art GNN method.
  arXiv  Detail & Related papers  (2026-06-15T04:45:41Z)
• Spatio-Temporal Attention Graph Neural Network: Explaining Causalities With Attention [0.0]
  Industrial Control Systems underpin critical infrastructure and face growing cyber-physical threats.<n>Machine learning-based anomaly detection approaches in ICS shows strong theoretical performance.<n>We propose a Spatio-Temporal Attention Graph Neural Network (STA-GNN) for unsupervised and explainable anomaly detection in ICS.
  arXiv  Detail & Related papers  (2026-03-11T11:41:38Z)
• GraFSTNet: Graph-based Frequency SpatioTemporal Network for Cellular Traffic Prediction [9.622104744379675]
  We propose a cellular traffic prediction framework that integrates temporal-temporal modeling with time-frequency analysis.<n>We introduce an adaptive-scale Logosh loss function, which adjusts the error penalty based on traffic magnitude.<n> Experiments on three open-sourced datasets demonstrate that the proposed method achieves prediction performance superior to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-02-06T16:21:06Z)
• Wireless Traffic Prediction with Large Language Model [54.07581399989292]
  TIDES is a novel framework that captures spatial-temporal correlations for wireless traffic prediction.<n> TIDES achieves efficient adaptation to domain-specific patterns without incurring excessive training overhead.<n>Our results indicate that integrating spatial awareness into LLM-based predictors is the key to unlocking scalable and intelligent network management in future 6G systems.
  arXiv  Detail & Related papers  (2025-12-19T04:47:40Z)
• Topology-Aware Conformal Prediction for Stream Networks [68.02503121089633]
  We propose Spatio-Temporal Adaptive Conformal Inference (textttCISTA), a novel framework that integrates network topology and temporal dynamics into the conformal prediction framework.<n>Our results show that textttCISTA effectively balances prediction efficiency and coverage, outperforming existing conformal prediction methods for stream networks.
  arXiv  Detail & Related papers  (2025-03-06T21:21:15Z)
• SFADNet: Spatio-temporal Fused Graph based on Attention Decoupling Network for Traffic Prediction [4.868638426254428]
  This paper proposes an innovative traffic flow prediction network, SFADNet, which categorizes traffic flow into multiple traffic patterns based on spatial feature matrices.<n>For each pattern, we construct an independent adaptive-temporal fusion graph based on a cross-attention mechanism, employing residual graph convolution modules and time series modules.<n>Extensive experimental results demonstrate that SFADNet outperforms current state-of-the-art baseline across large four-scale datasets.
  arXiv  Detail & Related papers  (2025-01-07T09:09:50Z)
• Physics-guided Active Sample Reweighting for Urban Flow Prediction [75.24539704456791]
  Urban flow prediction is a nuanced-temporal modeling that estimates the throughput of transportation services like buses, taxis and ride-driven models. Some recent prediction solutions bring remedies with the notion of physics-guided machine learning (PGML) We develop a atized physics-guided network (PN), and propose a data-aware framework Physics-guided Active Sample Reweighting (P-GASR)
  arXiv  Detail & Related papers  (2024-07-18T15:44:23Z)
• Probabilistically Rewired Message-Passing Neural Networks [41.554499944141654]
  Message-passing graph neural networks (MPNNs) emerged as powerful tools for processing graph-structured input. MPNNs operate on a fixed input graph structure, ignoring potential noise and missing information. We devise probabilistically rewired MPNNs (PR-MPNNs) which learn to add relevant edges while omitting less beneficial ones.
  arXiv  Detail & Related papers  (2023-10-03T15:43:59Z)
• ST-MLP: A Cascaded Spatio-Temporal Linear Framework with Channel-Independence Strategy for Traffic Forecasting [47.74479442786052]
  Current research on Spatio-Temporal Graph Neural Networks (STGNNs) often prioritizes complex designs, leading to computational burdens with only minor enhancements in accuracy. We propose ST-MLP, a concise cascaded temporal-temporal model solely based on Multi-Layer Perceptron (MLP) modules and linear layers. Empirical results demonstrate that ST-MLP outperforms state-of-the-art STGNNs and other models in terms of accuracy and computational efficiency.
  arXiv  Detail & Related papers  (2023-08-14T23:34:59Z)

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.