What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decomposition

• URL: http://arxiv.org/abs/2605.13032v2
• Date: Thu, 14 May 2026 02:41:44 GMT
• Title: What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decomposition
• Abstract summary: Graph neural networks are widely used for node classification, but they remain vulnerable to out-of-distribution (OOD) shifts in node features and graph structure.<n>We propose TIDE, a novel and effective Tri-Component Information Decomposition framework that explicitly decomposes information into feature-specific, structure-specific and joint components.<n>Extensive experiments across seven datasets confirm the efficacy of TIDE, achieving up to a 34% improvement in FPR95 over strong baselines.
• Score: 36.08108046941572
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph neural networks are widely used for node classification, but they remain vulnerable to out-of-distribution (OOD) shifts in node features and graph structure. Prior work established that methods trained with standard supervised learning (SL) objectives tend to capture spurious signals from either features and/or structure, leaving the model fragile under distributional changes. To address this, we propose TIDE, a novel and effective Tri-Component Information Decomposition framework that explicitly decomposes information into feature-specific, structure-specific and joint components. TIDE aims to preserve only the label-relevant part of the joint information while filtering out spurious feature- and structure-specific information, thereby enhancing the separation between in-distribution (ID) and OOD nodes. Beyond the framework, we provide theoretical and empirical analyses showing that an information bottleneck objective is preferable to standard SL for graph OOD detection, with higher ID confidence and a greater entropy gap between ID and OOD data. Extensive experiments across seven datasets confirm the efficacy of TIDE, achieving up to a 34% improvement in FPR95 over strong baselines while maintaining competitive ID accuracy.

Related papers

• LLM-Enhanced Energy Contrastive Learning for Out-of-Distribution Detection in Text-Attributed Graphs [29.764048070305254]
  We propose a novel approach, which integrates large language models (LLMs) and energy-based contrastive learning.<n>Our method consistently outperforms state-of-the-art baselines, achieving both high classification accuracy and robust OOD detection capabilities.
  arXiv  Detail & Related papers  (2026-03-19T02:48:46Z)
• Exploiting Inter-Sample Information for Long-tailed Out-of-Distribution Detection [7.0229899259286945]
  We show that exploiting inter-sample relationships can significantly improve OOD detection in long-tailed recognition of vision datasets.<n>Our method outperforms the state-of-the-art approaches by a large margin in terms of FPR and tail-class ID classification accuracy.
  arXiv  Detail & Related papers  (2025-11-20T03:31:37Z)
• Structural and Statistical Texture Knowledge Distillation and Learning for Segmentation [70.15341084443236]
  We re-emphasize the low-level texture information in deep networks for semantic segmentation and related knowledge distillation tasks.<n>We propose a novel Structural and Statistical Texture Knowledge Distillation (SSTKD) framework for semantic segmentation.<n>Specifically, Contourlet Decomposition Module (CDM) is introduced to decompose the low-level features.<n> Texture Intensity Equalization Module (TIEM) is designed to extract and enhance the statistical texture knowledge.
  arXiv  Detail & Related papers  (2025-03-11T04:49:25Z)
• Structural Entropy Guided Unsupervised Graph Out-Of-Distribution Detection [11.217628543343855]
  Unsupervised out-of-distribution (OOD) detection is vital for ensuring the reliability of graph neural networks (GNNs)<n>Existing methods often suffer from compromised performance due to redundant information in graph structures.<n>We propose SEGO, an unsupervised framework that integrates structural entropy into OOD detection.
  arXiv  Detail & Related papers  (2025-03-05T07:47:57Z)
• HELPNet: Hierarchical Perturbations Consistency and Entropy-guided Ensemble for Scribble Supervised Medical Image Segmentation [4.034121387622003]
  We propose HELPNet, a novel scribble-based weakly supervised segmentation framework.<n>HELPNet integrates three modules to bridge the gap between annotation efficiency and segmentation performance.<n>HELPNet significantly outperforms state-of-the-art methods for scribble-based weakly supervised segmentation.
  arXiv  Detail & Related papers  (2024-12-25T01:52:01Z)
• What If the Input is Expanded in OOD Detection? [77.37433624869857]
  Out-of-distribution (OOD) detection aims to identify OOD inputs from unknown classes. Various scoring functions are proposed to distinguish it from in-distribution (ID) data. We introduce a novel perspective, i.e., employing different common corruptions on the input space.
  arXiv  Detail & Related papers  (2024-10-24T06:47:28Z)
• 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)
• Out-of-distribution detection based on subspace projection of high-dimensional features output by the last convolutional layer [5.902332693463877]
  This paper concentrates on the high-dimensional features output by the final convolutional layer, which contain rich image features. Our key idea is to project these high-dimensional features into two specific feature subspaces, trained with Predefined Evenly-Distribution Class Centroids (PEDCC)-Loss. Our method requires only the training of the classification network model, eschewing any need for input pre-processing or specific OOD data pre-tuning.
  arXiv  Detail & Related papers  (2024-05-02T18:33:02Z)
• Structural and Statistical Texture Knowledge Distillation for Semantic Segmentation [72.19108372163868]
  We propose a novel Structural and Statistical Texture Knowledge Distillation (SSTKD) framework for semantic segmentation.<n>For structural texture knowledge, we introduce a Contourlet Decomposition Module (CDM) that decomposes low-level features.<n>For statistical texture knowledge, we propose a Denoised Texture Intensity Equalization Module (DTIEM) to adaptively extract and enhance statistical texture knowledge.
  arXiv  Detail & Related papers  (2023-05-06T06:01:11Z)
• Energy-based Out-of-Distribution Detection for Graph Neural Networks [76.0242218180483]
  We propose a simple, powerful and efficient OOD detection model for GNN-based learning on graphs, which we call GNNSafe. GNNSafe achieves up to $17.0%$ AUROC improvement over state-of-the-arts and it could serve as simple yet strong baselines in such an under-developed area.
  arXiv  Detail & Related papers  (2023-02-06T16:38:43Z)
• Span Classification with Structured Information for Disfluency Detection in Spoken Utterances [47.05113261111054]
  We propose a novel architecture for detecting disfluencies in transcripts from spoken utterances. Our proposed model achieves state-of-the-art results on the widely used English Switchboard for disfluency detection.
  arXiv  Detail & Related papers  (2022-03-30T03:22:29Z)
• Graph Information Bottleneck [77.21967740646784]
  Graph Neural Networks (GNNs) provide an expressive way to fuse information from network structure and node features. Inheriting from the general Information Bottleneck (IB), GIB aims to learn the minimal sufficient representation for a given task. We show that our proposed models are more robust than state-of-the-art graph defense models.
  arXiv  Detail & Related papers  (2020-10-24T07:13:00Z)

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.