FSX: Message Flow Sensitivity Enhanced Structural Explainer for Graph Neural Networks

• URL: http://arxiv.org/abs/2601.14730v1
• Date: Wed, 21 Jan 2026 07:39:42 GMT
• Title: FSX: Message Flow Sensitivity Enhanced Structural Explainer for Graph Neural Networks
• Authors: Bizu Feng, Zhimu Yang, Shaode Yu, Zixin Hu,
• Abstract summary: We propose a novel framework that combines internal message flows of the model with a cooperative game approach applied to external graph data.<n> FSX achieves superior explanation fidelity with significantly reduced runtime.<n>It provides unprecedented insights into the structural logic underlying model predictions.
• Score: 1.6916040234975795
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite the widespread success of Graph Neural Networks (GNNs), understanding the reasons behind their specific predictions remains challenging. Existing explainability methods face a trade-off that gradient-based approaches are computationally efficient but often ignore structural interactions, while game-theoretic techniques capture interactions at the cost of high computational overhead and potential deviation from the model's true reasoning path. To address this gap, we propose FSX (Message Flow Sensitivity Enhanced Structural Explainer), a novel hybrid framework that synergistically combines the internal message flows of the model with a cooperative game approach applied to the external graph data. FSX first identifies critical message flows via a novel flow-sensitivity analysis: during a single forward pass, it simulates localized node perturbations and measures the resulting changes in message flow intensities. These sensitivity-ranked flows are then projected onto the input graph to define compact, semantically meaningful subgraphs. Within each subgraph, a flow-aware cooperative game is conducted, where node contributions are evaluated fairly through a Shapley-like value that incorporates both node-feature importance and their roles in sustaining or destabilizing the identified critical flows. Extensive evaluation across multiple datasets and GNN architectures demonstrates that FSX achieves superior explanation fidelity with significantly reduced runtime, while providing unprecedented insights into the structural logic underlying model predictions--specifically, how important sub-structures exert influence by governing the stability of key internal computational pathways.

Related papers

• InteractiveGNNExplainer: A Visual Analytics Framework for Multi-Faceted Understanding and Probing of Graph Neural Network Predictions [0.0]
  Graph Neural Networks (GNNs) excel in graph-based learning tasks, but their complex, non-linear operations often render them as opaque "black boxes"<n>This paper introduces InteractiveGNNExplainer, a visual analytics framework to enhance GNN explainability.
  arXiv  Detail & Related papers  (2025-11-17T09:08:31Z)
• Graph Flow Matching: Enhancing Image Generation with Neighbor-Aware Flow Fields [19.09766809443072]
  Flow matching casts sample generation as learning a continuous-time velocity field that transports noise to data.<n>We propose Graph Flow Matching, a lightweight enhancement that decomposes the learned velocity into a reaction term.<n> operating in the latent space of a pretrained variational autoencoder.
  arXiv  Detail & Related papers  (2025-05-30T10:17:50Z)
• PIORF: Physics-Informed Ollivier-Ricci Flow for Long-Range Interactions in Mesh Graph Neural Networks [23.97389618896843]
  We propose Physics-Informed Ollivier-Ricci Flow (PIORF), a novel rewiring method that combines physical correlations with graph topology.<n>We show that PIORF consistently outperforms baseline models and existing rewiring methods, achieving up to 26.2 improvement.
  arXiv  Detail & Related papers  (2025-04-05T04:14:05Z)
• Learning to Model Graph Structural Information on MLPs via Graph Structure Self-Contrasting [50.181824673039436]
  We propose a Graph Structure Self-Contrasting (GSSC) framework that learns graph structural information without message passing. The proposed framework is based purely on Multi-Layer Perceptrons (MLPs), where the structural information is only implicitly incorporated as prior knowledge. It first applies structural sparsification to remove potentially uninformative or noisy edges in the neighborhood, and then performs structural self-contrasting in the sparsified neighborhood to learn robust node representations.
  arXiv  Detail & Related papers  (2024-09-09T12:56:02Z)
• XG-NID: Dual-Modality Network Intrusion Detection using a Heterogeneous Graph Neural Network and Large Language Model [5.298018090482744]
  "XG-NID" is the first to fuse flow-level and packet-level data within a heterogeneous graph structure.<n>XG-NID uniquely enables real-time inference while effectively capturing the intricate relationships between flow and packet payload data.
  arXiv  Detail & Related papers  (2024-08-27T01:14:34Z)
• A Pure Transformer Pretraining Framework on Text-attributed Graphs [50.833130854272774]
  We introduce a feature-centric pretraining perspective by treating graph structure as a prior. Our framework, Graph Sequence Pretraining with Transformer (GSPT), samples node contexts through random walks. GSPT can be easily adapted to both node classification and link prediction, demonstrating promising empirical success on various datasets.
  arXiv  Detail & Related papers  (2024-06-19T22:30:08Z)
• Revealing Decurve Flows for Generalized Graph Propagation [108.80758541147418]
  This study addresses the limitations of the traditional analysis of message-passing, central to graph learning, by defining em textbfgeneralized propagation with directed and weighted graphs. We include a preliminary exploration of learned propagation patterns in datasets, a first in the field.
  arXiv  Detail & Related papers  (2024-02-13T14:13:17Z)
• Chasing Fairness in Graphs: A GNN Architecture Perspective [73.43111851492593]
  We propose textsfFair textsfMessage textsfPassing (FMP) designed within a unified optimization framework for graph neural networks (GNNs) In FMP, the aggregation is first adopted to utilize neighbors' information and then the bias mitigation step explicitly pushes demographic group node presentation centers together. Experiments on node classification tasks demonstrate that the proposed FMP outperforms several baselines in terms of fairness and accuracy on three real-world datasets.
  arXiv  Detail & Related papers  (2023-12-19T18:00:15Z)
• Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification [69.45543438974963]
  We find graph-based methods in the visible-infrared person re-identification task (VI-ReID) suffer from bad generalization because of two issues. The well-trained input features weaken the learning of graph topology, making it not generalized enough during the inference process. We propose a Counterfactual Intervention Feature Transfer (CIFT) method to tackle these problems.
  arXiv  Detail & Related papers  (2022-08-01T16:15:31Z)
• FlowX: Towards Explainable Graph Neural Networks via Message Flows [59.025023020402365]
  We investigate the explainability of graph neural networks (GNNs) as a step toward elucidating their working mechanisms. We propose a novel method here, known as FlowX, to explain GNNs by identifying important message flows. We then propose an information-controlled learning algorithm to train flow scores toward diverse explanation targets.
  arXiv  Detail & Related papers  (2022-06-26T22:48:15Z)

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.