Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic Graphs

• URL: http://arxiv.org/abs/2502.17912v2
• Date: Mon, 17 Mar 2025 08:23:08 GMT
• Title: Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic Graphs
• Authors: Yuhan Chen, Yihong Luo, Yifan Song, Pengwen Dai, Jing Tang, Xiaochun Cao,
• Abstract summary: OOD detection on nodes in graph learning remains underexplored.<n>GNNSafe adapted energy-based detection to the graph domain with state-of-the-art performance.<n>We introduce DeGEM, which decomposes the learning process into two parts: a graph encoder that leverages topology information for node representations and an energy head that operates in latent space.
• Score: 61.226857589092
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite extensive research efforts focused on OOD detection on images, OOD detection on nodes in graph learning remains underexplored. The dependence among graph nodes hinders the trivial adaptation of existing approaches on images that assume inputs to be i.i.d. sampled, since many unique features and challenges specific to graphs are not considered, such as the heterophily issue. Recently, GNNSafe, which considers node dependence, adapted energy-based detection to the graph domain with state-of-the-art performance, however, it has two serious issues: 1) it derives node energy from classification logits without specifically tailored training for modeling data distribution, making it less effective at recognizing OOD data; 2) it highly relies on energy propagation, which is based on homophily assumption and will cause significant performance degradation on heterophilic graphs, where the node tends to have dissimilar distribution with its neighbors. To address the above issues, we suggest training EBMs by MLE to enhance data distribution modeling and remove energy propagation to overcome the heterophily issues. However, training EBMs via MLE requires performing MCMC sampling on both node feature and node neighbors, which is challenging due to the node interdependence and discrete graph topology. To tackle the sampling challenge, we introduce DeGEM, which decomposes the learning process into two parts: a graph encoder that leverages topology information for node representations and an energy head that operates in latent space. Extensive experiments validate that DeGEM, without OOD exposure during training, surpasses previous state-of-the-art methods, achieving an average AUROC improvement of 6.71% on homophilic graphs and 20.29% on heterophilic graphs, and even outperform methods trained with OOD exposure. Our code is available at: https://github.com/draym28/DeGEM.

Related papers

• Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity [9.520967269079007]
  Graph anomaly detection (GAD) aims to identify nodes from a graph that are significantly different from normal patterns.<n>Most previous studies are model-driven, focusing on enhancing the detection effect by improving the model structure.<n>We introduce graph curriculum learning as a simple and effective plug-and-play module to optimize GAD methods.
  arXiv  Detail & Related papers  (2025-01-24T03:01:16Z)
• Counterfactual Data Augmentation with Denoising Diffusion for Graph Anomaly Detection [32.165578819142695]
  We propose CAGAD -- an unsupervised Counterfactual data Augmentation method for Graph Anomaly Detection. We design a graph-specific diffusion model to translate a part of its neighbors, which are probably normal, into anomalous ones. Through aggregating the translated anomalous neighbors, counterfactual representations become more distinguishable and further advocate detection performance.
  arXiv  Detail & Related papers  (2024-07-02T10:37:54Z)
• Multitask Active Learning for Graph Anomaly Detection [48.690169078479116]
  We propose a novel MultItask acTIve Graph Anomaly deTEction framework, namely MITIGATE. By coupling node classification tasks, MITIGATE obtains the capability to detect out-of-distribution nodes without known anomalies. Empirical studies on four datasets demonstrate that MITIGATE significantly outperforms the state-of-the-art methods for anomaly detection.
  arXiv  Detail & Related papers  (2024-01-24T03:43:45Z)
• Data Augmentation for Supervised Graph Outlier Detection via Latent Diffusion Models [39.33024157496401]
  We introduce GODM, a novel data augmentation for mitigating class imbalance in supervised graph outlier detection. Extensive experiments conducted on multiple datasets substantiate the effectiveness and efficiency of GODM. We encapsulate GODM into a plug-and-play package and release it at PyPI.
  arXiv  Detail & Related papers  (2023-12-29T16:50:40Z)
• Breaking the Entanglement of Homophily and Heterophily in Semi-supervised Node Classification [25.831508778029097]
  We introduce AMUD, which quantifies the relationship between node profiles and topology from a statistical perspective. We also propose ADPA as a new directed graph learning paradigm for AMUD.
  arXiv  Detail & Related papers  (2023-12-07T07:54:11Z)
• BOURNE: Bootstrapped Self-supervised Learning Framework for Unified Graph Anomaly Detection [50.26074811655596]
  We propose a novel unified graph anomaly detection framework based on bootstrapped self-supervised learning (named BOURNE) By swapping the context embeddings between nodes and edges, we enable the mutual detection of node and edge anomalies. BOURNE can eliminate the need for negative sampling, thereby enhancing its efficiency in handling large graphs.
  arXiv  Detail & Related papers  (2023-07-28T00:44:57Z)
• Addressing Heterophily in Node Classification with Graph Echo State Networks [11.52174067809364]
  We address the challenges of heterophilic graphs with Graph Echo State Network (GESN) for node classification. GESN is a reservoir computing model for graphs, where node embeddings are computed by an untrained message-passing function. Our experiments show that reservoir models are able to achieve better or comparable accuracy with respect to most fully trained deep models.
  arXiv  Detail & Related papers  (2023-05-14T19:42:31Z)
• 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)
• Resisting Graph Adversarial Attack via Cooperative Homophilous Augmentation [60.50994154879244]
  Recent studies show that Graph Neural Networks are vulnerable and easily fooled by small perturbations. In this work, we focus on the emerging but critical attack, namely, Graph Injection Attack. We propose a general defense framework CHAGNN against GIA through cooperative homophilous augmentation of graph data and model.
  arXiv  Detail & Related papers  (2022-11-15T11:44:31Z)
• Heterogeneous Graph Neural Networks using Self-supervised Reciprocally Contrastive Learning [102.9138736545956]
  Heterogeneous graph neural network (HGNN) is a very popular technique for the modeling and analysis of heterogeneous graphs. We develop for the first time a novel and robust heterogeneous graph contrastive learning approach, namely HGCL, which introduces two views on respective guidance of node attributes and graph topologies. In this new approach, we adopt distinct but most suitable attribute and topology fusion mechanisms in the two views, which are conducive to mining relevant information in attributes and topologies separately.
  arXiv  Detail & Related papers  (2022-04-30T12:57:02Z)

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.