Out-of-distribution (OOD) node detection in graphs is a critical yet challenging task. Most existing approaches rely heavily on fine-grained labeled data to obtain a pretrained supervised classifier, inherently assuming the existence of a well-defined pretext classification task. However, when such a task is ill-defined or absent, their applicability becomes severely limited. To overcome this limitation, there is an urgent need to propose a more scalable OOD detection method that is independent of both pretext tasks and label supervision. We harness a new phenomenon called Feature Resonance, focusing on the feature space rather than the label space. We observe that, ideally, during the optimization of known ID samples, unknown ID samples undergo more significant representation changes than OOD samples, even when the model is trained to align arbitrary targets. The rationale behind it is that even without gold labels, the local manifold may still exhibit smooth resonance. Based on this, we further develop a novel graph OOD framework, dubbed Resonance-based Separation and Learning (RSL), which comprises two core modules: (i)-a more practical micro-level proxy of feature resonance that measures the movement of feature vectors in one training step.

Graph Neural Networks (GNNs) are increasingly deployed in mission-critical tasks, yet they often encounter inputs that lie outside their training distribution, leading to unreliable or overconfident predictions. To address this limitation, we present RAGNOR (Robust Aggregation Graph Norm for Outlier Recognition), a post-hoc approach that leverages embedding norms for robust out-of-distribution (OOD) detection on both node-level and graph-level tasks. Unlike previous methods designed primarily for image domains, RAGNOR directly tackles the relational challenges intrinsic to graphs: local contamination by anomalous neighbors, disparate norm scales across classes or roles, and insufficient references for boundary or low-degree nodes.

GPN applies a personalized page rank (PPR) module to diffuse the evidence among neighboring nodes.

GPN applies a personalized page rank (PPR) module to diffuse the evidence among neighboring nodes.

Out-of-distribution (OOD) detection in graphs is critical for ensuring model robustness in open-world and safety-sensitive applications. Existing graph OOD detection approaches typically train an in-distribution (ID) classifier on ID data alone, then apply post-hoc scoring to detect OOD instances. While OOD exposure - adding auxiliary OOD samples during training - can improve detection, current graph-based methods often assume access to real OOD nodes, which is often impractical or costly. In this paper, we present GOE-LLM, a framework that leverages Large Language Models (LLMs) to achieve OOD exposure on text-attributed graphs without using any real OOD nodes. GOE-LLM introduces two pipelines: (1) identifying pseudo-OOD nodes from the initially unlabeled graph using zero-shot LLM annotations, and (2) generating semantically informative synthetic OOD nodes via LLM-prompted text generation. These pseudo-OOD nodes are then used to regularize ID classifier training and enhance OOD detection awareness. Empirical results on multiple benchmarks show that GOE-LLM substantially outperforms state-of-the-art methods without OOD exposure, achieving up to a 23.5% improvement in AUROC for OOD detection, and attains performance on par with those relying on real OOD labels for exposure.

Out-of-Distribution Detection in Heterogeneous Graphs via Energy Propagation Tao Yin a, Chen Zhao b, Xiaoyan Liu c and Minglai Shao a, a School of New Media and Communication, Tianjin University, Tianjin, China b Department of Computer Science, Baylor University, Texas, USA c School of Qiyue Media and Communication, Cangzhou Normal University, Hebei, ChinaA R T I C L E I N F OKeywords: Heterogeneous Graph Out-of-distribution Detection Energy A B S T R A C T Graph neural networks (GNNs) are proven effective in extracting complex node and structural information from graph data. While current GNNs perform well in node classification tasks within in-distribution (ID) settings, real-world scenarios often present distribution shifts, leading to the presence of out-of-distribution (OOD) nodes. OOD detection in graphs is a crucial and challenging task. Most existing research focuses on homogeneous graphs, but real-world graphs are often heterogeneous, consisting of diverse node and edge types. This heterogeneity adds complexity and enriches the informational content. To the best of our knowledge, OOD detection in heterogeneous graphs remains an underexplored area. In this context, we propose a novel methodology for OOD detection in heterogeneous graphs (OODHG) that aims to achieve two main objectives: 1) detecting OOD nodes and 2) classifying all ID nodes based on the first task's results. Specifically, we learn representations for each node in the heterogeneous graph, calculate energy values to determine whether nodes are OOD, and then classify ID nodes. To leverage the structural information of heterogeneous graphs, we introduce a meta-path-based energy propagation mechanism and an energy constraint to enhance the distinction between ID and OOD nodes. Extensive experimental findings substantiate the simplicity and effectiveness of OODHG, demonstrating its superiority over baseline models in OOD detection tasks and its accuracy in ID node classification.1. Introduction The rapid progression of graph neural networks (GNNs) has profoundly impacted various domains, where graph data play a crucial role. GNNs can extract rich structural information from graphs. This enables them to effectively model complex relationships in graph data [25]. This capability has driven their widespread adoption across a diverse range of domains, including social networks, knowledge graphs, the world wide web, and numerous others.

Existing methods for graph out-of-distribution (OOD) detection typically depend on training graph neural network (GNN) classifiers using a substantial amount of labeled in-distribution (ID) data. However, acquiring high-quality labeled nodes in text-attributed graphs (TAGs) is challenging and costly due to their complex textual and structural characteristics. Large language models (LLMs), known for their powerful zero-shot capabilities in textual tasks, show promise but struggle to naturally capture the critical structural information inherent to TAGs, limiting their direct effectiveness. To address these challenges, we propose LLM-GOOD, a general framework that effectively combines the strengths of LLMs and GNNs to enhance data efficiency in graph OOD detection. Specifically, we first leverage LLMs' strong zero-shot capabilities to filter out likely OOD nodes, significantly reducing the human annotation burden. To minimize the usage and cost of the LLM, we employ it only to annotate a small subset of unlabeled nodes. We then train a lightweight GNN filter using these noisy labels, enabling efficient predictions of ID status for all other unlabeled nodes by leveraging both textual and structural information. After obtaining node embeddings from the GNN filter, we can apply informativeness-based methods to select the most valuable nodes for precise human annotation. Finally, we train the target ID classifier using these accurately annotated ID nodes. Extensive experiments on four real-world TAG datasets demonstrate that LLM-GOOD significantly reduces human annotation costs and outperforms state-of-the-art baselines in terms of both ID classification accuracy and OOD detection performance.

Detecting out-of-distribution (OOD) nodes in the graph-based machine-learning field is challenging, particularly when in-distribution (ID) node multi-category labels are unavailable. Thus, we focus on feature space rather than label space and find that, ideally, during the optimization of known ID samples, unknown ID samples undergo more significant representation changes than OOD samples, even if the model is trained to fit random targets, which we called the Feature Resonance phenomenon. The rationale behind it is that even without gold labels, the local manifold may still exhibit smooth resonance. Based on this, we further develop a novel graph OOD framework, dubbed Resonance-based Separation and Learning (RSL), which comprises two core modules: (i) a more practical micro-level proxy of feature resonance that measures the movement of feature vectors in one training step. (ii) integrate with synthetic OOD nodes strategy to train an effective OOD classifier. Theoretically, we derive an error bound showing the superior separability of OOD nodes during the resonance period. Empirically, RSL achieves state-of-the-art performance, reducing the FPR95 metric by an average of 18.51% across five real-world datasets.