GLASS：基于球形评分的图-语言对齐的可迁移图级异常检测框架
GLASS: Graph-Language Alignment with Spherical Scoring for Transferable Graph-Level Anomaly Detection
浏览论文内容
中文总结 AI 辅助
该研究提出GLASS框架，通过图-语言对齐与球形多模态评分实现图级异常检测，在12个基准和3个元域上取得最优性能，支持零样本及少样本跨域迁移。
中文摘要 AI 辅助
我们提出GLASS，这是一种用于图级异常检测（GLAD）的框架，通过在单位超球面上进行图-语言对齐实现了稳健的跨域迁移性。GLASS通过多片软余弦目标函数将感知结构的图编码器与感知指令的文本嵌入对齐，构建了统一的表示空间。我们的框架将图的局部、全局和语义属性序列化为紧凑的图描述符提示（GraphDP），创建了一个与领域无关的异常评分的文本桥梁。通过嵌套表示片强制执行多尺度一致性，模型能够捕获不同粒度级别的异常偏差。对于评分，我们将异常检测公式化为对齐超球面上的密度估计，并引入球形多模态评分（SMS），其在图和文本嵌入空间中实例化了von Mises-Fisher核密度估计器。这种概率公式在高浓度极限情况下恢复了角k近邻评分，并提供了结构和语义异常信号的原则性融合。共享的文本嵌入空间进一步充当跨域桥梁：通过编码目标域的GraphDP而无需目标域的训练数据，GLASS执行零样本异常检测；仅使用少量正常示例时，通过参考集校准实现少样本适应。在12个基准和3个元域上，与最近的先进GLAD基线相比，GLASS获得了最佳的平均AUROC和排名，并实现了有效的跨域迁移。
英文摘要
We introduce GLASS, a framework for graph-level anomaly detection (GLAD) that achieves robust cross-domain transferability through graph-language alignment on the unit hypersphere. GLASS builds a unified representation space by aligning a structure-aware graph encoder with an instruction-aware text embedding via a multi-slice soft cosine objective. Our framework serializes local, global, and semantic graph properties into a compact Graph Descriptor Prompt (GraphDP), creating a text bridge that enables domain-agnostic anomaly scoring. By enforcing multi-scale consistency through Matryoshka representation slices, the model captures anomalous deviations at multiple levels of granularity. We formulate anomaly detection as density estimation on the aligned hypersphere and introduce Spherical Multi-Modal Scoring (SMS), which instantiates von Mises-Fisher kernel density estimators in both graph and text embedding spaces. This probabilistic formulation recovers angular 1-nearest-neighbor scoring in the high-concentration limit, motivates the practical mean k-nearest-neighbor scorer, and provides a principled fusion of structural and semantic anomaly signals. The shared text embedding space further serves as a cross-domain bridge: by encoding a target domain's GraphDP without target-domain training data, GLASS performs zero-shot anomaly detection, and with only a handful of normal examples, few-shot adaptation via reference-set calibration. For privacy-sensitive deployment, we extend reference-set calibration with a bounded joint graph-text kernel summary that provides graph-record differential privacy while keeping the encoders fixed independently of the private target references. Across twelve benchmarks and three meta-domains, GLASS obtains the best average AUROC and rank compared with recent advanced GLAD baselines and enables effective cross-domain transfer.
发表机构
- School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen)（香港中文大学（深圳）数据科学学院）
机构由 AI 辅助整理，请以论文原文为准。
