用大模型生成假异常节点，让图模型更懂什么是异常。
Graph Synthetic Out-of-Distribution Exposure with Large Language Models
- 用零样本大模型标注图中潜在异常节点
- 通过提示词生成语义合理的虚假异常数据
- 无需真实异常数据，检测效果媲美有异常样本训练
图数据的异常检测对开放世界和高安全场景中的模型鲁棒性至关重要。现有方法通常仅在正常数据上训练分类器，再通过后处理识别异常。虽然引入异常数据（OOD暴露）可提升检测性能，但多数图方法依赖真实异常节点，实际难以获取。本文提出GOE-LLM框架，利用大语言模型在无真实异常节点的前提下，实现文本属性图的异常暴露。该框架包含两个流程：(1) 使用零样本大模型标注初始未标记图中的伪异常节点；(2) 通过大模型提示生成具有语义信息的合成异常节点。这些伪异常节点用于正则化正常分类器训练，增强模型对异常的感知能力。多基准测试结果表明，GOE-LLM显著优于无需异常暴露的现有方法，异常检测的AUROC最高提升23.5%，且性能接近依赖真实异常标签的方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。