GLIP-OOD: Zero-Shot Graph OOD Detection with Graph Foundation Model

2025/04/29 by Haoyan Xu, Xu, Haoyan, Xuzhi Zhang +14 · 5 citations
Computer Science · #Advanced Graph Neural Networks #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2504.21186

openalex publication_date 2025/04/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Out-of-distribution (OOD) detection is critical for ensuring the safety and reliability of machine learning systems, particularly in dynamic and open-world environments. In the vision and text domains, zero-shot OOD detection - which requires no training on in-distribution (ID) data - has advanced significantly through the use of large-scale pretrained models, such as vision-language models (VLMs) and large language models (LLMs). However, zero-shot OOD detection in graph-structured data remains largely unexplored, primarily due to the challenges posed by complex relational structures and the absence of powerful, large-scale pretrained models for graphs. In this work, we take the first step toward enabling zero-shot graph OOD detection by leveraging a graph foundation model (GFM). Our experiments show that, when provided only with class label names for both ID and OOD categories, the GFM can effectively perform OOD detection - often surpassing existing "supervised" OOD detection methods that rely on extensive labeled node data. We further address the practical scenario in which OOD label names are not available in real-world settings by introducing GLIP-OOD, a framework that uses LLMs to generate semantically informative pseudo-OOD labels from unlabeled data. These generated OOD labels allow the GFM to better separate ID and OOD classes, facilitating more precise OOD detection - all without any labeled nodes (only ID label names). To our knowledge, this is the first approach to achieve node-level graph OOD detection in a fully zero-shot setting, and it attains performance comparable to state-of-the-art supervised methods on four benchmark text-attributed graph datasets.

Citations

• Few-Shot Graph Out-of-Distribution Detection with LLMs
• Secure On-Device Video OOD Detection Without Backpropagation
• CMOOD: Concept-based Multi-label OOD Detection
• GraphCLIP: Enhancing Transferability in Graph Foundation Models for Text-Attributed Graphs
• MetaOOD: Automatic Selection of OOD Detection Models
• Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insights
• Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection
• Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detector
• CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No
• Energy-based Out-of-Distribution Detection for Graph Neural Networks
• Text Embeddings by Weakly-Supervised Contrastive Pre-training
• Delving into Out-of-Distribution Detection with Vision-Language Representations
• Recipe for a General, Powerful, Scalable Graph Transformer
• Towards Textual Out-of-Domain Detection without In-Domain Labels
• Generalized Out-of-Distribution Detection: A Survey
• Generalized Out-of-Distribution Detection: A Survey
• Learning Transferable Visual Models From Natural Language Supervision
• Trust Issues: Uncertainty Estimation Does Not Enable Reliable OOD Detection On Medical Tabular Data
• Energy-based Out-of-distribution Detection
• Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks
• DeBERTa: Decoding-enhanced BERT with Disentangled Attention
• MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers
• Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Cited by

• LLM-Powered Text-Attributed Graph Anomaly Detection via Retrieval-Augmented Reasoning
• Large Language Models Meet Text-Attributed Graphs: A Survey of Integration Frameworks and Applications
• Text Meets Topology: Rethinking Out-of-distribution Detection in Text-Rich Networks
• M3OOD: Automatic Selection of Multimodal OOD Detectors
• When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty

Related

• Graph Synthetic Out-of-Distribution Exposure with Large Language Models
• Few-Shot Graph Out-of-Distribution Detection with LLMs
• GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generation
• Bridging OOD Detection and Generalization: A Graph-Theoretic View
• Coarse-to-Fine Open-Set Graph Node Classification with Large Language Models