LLM-Enhanced Energy Contrastive Learning for Out-of-Distribution Detection in Text-Attributed Graphs

• URL: http://arxiv.org/abs/2603.20293v1
• Date: Thu, 19 Mar 2026 02:48:46 GMT
• Title: LLM-Enhanced Energy Contrastive Learning for Out-of-Distribution Detection in Text-Attributed Graphs
• Abstract summary: 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.
• Score: 29.764048070305254
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-attributed graphs, where nodes are enriched with textual attributes, have become a powerful tool for modeling real-world networks such as citation, social, and transaction networks. However, existing methods for learning from these graphs often assume that the distributions of training and testing data are consistent. This assumption leads to significant performance degradation when faced with out-of-distribution (OOD) data. In this paper, we address the challenge of node-level OOD detection in text-attributed graphs, with the goal of maintaining accurate node classification while simultaneously identifying OOD nodes. We propose a novel approach, LLM-Enhanced Energy Contrastive Learning for Out-of-Distribution Detection in Text-Attributed Graphs (LECT), which integrates large language models (LLMs) and energy-based contrastive learning. The proposed method involves generating high-quality OOD samples by leveraging the semantic understanding and contextual knowledge of LLMs to create dependency-aware pseudo-OOD nodes, and applying contrastive learning based on energy functions to distinguish between in-distribution (IND) and OOD nodes. The effectiveness of our method is demonstrated through extensive experiments on six benchmark datasets, where our method consistently outperforms state-of-the-art baselines, achieving both high classification accuracy and robust OOD detection capabilities.

Related papers

• Learning to Explore: Policy-Guided Outlier Synthesis for Graph Out-of-Distribution Detection [51.93878677594561]
  In unsupervised graph-level OOD detection, models are typically trained using only in-distribution (ID) data.<n>We propose a Policy-Guided Outlier Synthesis framework that replaces statics with a learned exploration strategy.
  arXiv  Detail & Related papers  (2026-02-28T11:40:18Z)
• From Subtle to Significant: Prompt-Driven Self-Improving Optimization in Test-Time Graph OOD Detection [15.167705236111104]
  Graph Out-of-Distribution (OOD) detection aims to identify whether a test graph deviates from the distribution observed during training.<n>We propose a textbfSelf-textbfIm textbfGraph textbfOut-textbfof-textbfDistribution detector (SIGOOD)<n>SIGOOD generates a prompt to construct a prompt-enhanced graph that amplifies potential OOD signals.
  arXiv  Detail & Related papers  (2026-02-19T13:19:53Z)
• Both Topology and Text Matter: Revisiting LLM-guided Out-of-Distribution Detection on Text-attributed Graphs [9.174883084149881]
  LG-Plug is an LLM-Guided Plug-and-play strategy for TAG OOD detection tasks.<n>It generates consensus-driven OOD exposure via clustered iterative prompting.<n>The resulting OOD exposure serves as a regularization term to separate ID and OOD nodes, enabling seamless integration with existing detectors.
  arXiv  Detail & Related papers  (2026-02-12T06:53:35Z)
• Revisiting Logit Distributions for Reliable Out-of-Distribution Detection [73.9121001113687]
  Out-of-distribution (OOD) detection is critical for ensuring the reliability of deep learning models in open-world applications.<n>LogitGap is a novel post-hoc OOD detection method that exploits the relationship between the maximum logit and the remaining logits.<n>We show that LogitGap consistently achieves state-of-the-art performance across diverse OOD detection scenarios and benchmarks.
  arXiv  Detail & Related papers  (2025-10-23T02:16:45Z)
• Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection [71.59834293521074]
  We develop a framework to distinguish between human-authored and machine-generated text.<n>Our method achieves 98.3% AUROC and AUPR with only 8.9% FPR95 on DeepFake dataset.<n>Code, pretrained weights, and demo will be released.
  arXiv  Detail & Related papers  (2025-10-07T08:14:45Z)
• Graph Synthetic Out-of-Distribution Exposure with Large Language Models [14.666576854790163]
  Out-of-distribution (OOD) detection in graphs is critical for ensuring model robustness in open-world and safety-sensitive applications.<n>Current graph-based methods often assume access to real OOD nodes, which is often impractical or costly.<n>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.
  arXiv  Detail & Related papers  (2025-04-29T22:04:30Z)
• Few-Shot Graph Out-of-Distribution Detection with LLMs [34.42512005781724]
  We propose a framework that combines the strengths of large language models (LLMs) and graph neural networks (GNNs) to enhance data efficiency in graph out-of-distribution (OOD) detection.<n>We show 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.
  arXiv  Detail & Related papers  (2025-03-28T02:37:18Z)
• Enhancing OOD Detection Using Latent Diffusion [3.4899193297791054]
  Out-of-distribution (OOD) detection is crucial for the reliable deployment of machine learning models in real-world scenarios.<n>Recent efforts have explored using generative models, such as Stable Diffusion, to synthesize outlier data in the pixel space.<n>We propose Outlier-Aware Learning (OAL), a novel framework that generates synthetic OOD training data within the latent space.
  arXiv  Detail & Related papers  (2024-06-24T11:01:43Z)
• 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)
• GOOD-D: On Unsupervised Graph Out-Of-Distribution Detection [67.90365841083951]
  We develop a new graph contrastive learning framework GOOD-D for detecting OOD graphs without using any ground-truth labels. GOOD-D is able to capture the latent ID patterns and accurately detect OOD graphs based on the semantic inconsistency in different granularities. As a pioneering work in unsupervised graph-level OOD detection, we build a comprehensive benchmark to compare our proposed approach with different state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-11-08T12:41:58Z)
• Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentation [76.2621758731288]
  We tackle the detection of out-of-distribution (OOD) objects in semantic segmentation. Our main contribution is a new OOD detection architecture called ObsNet associated with a dedicated training scheme based on Local Adversarial Attacks (LAA) We show it obtains top performances both in speed and accuracy when compared to ten recent methods of the literature on three different datasets.
  arXiv  Detail & Related papers  (2021-08-03T17:09:56Z)

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.