AuraTracer智迹闻
中文

EVENT DOSSIER

GLASS: Graph-Language Alignment with Spherical Scoring for Transferable Graph-Level Anomaly Detection

2026-09-07 12:00 Models across 2 days 🔥 47.2 heat score
2sources
2days unfolding
47.2heat score
1mentions
SummaryAI generated

The `GLASS framework proposes a robust cross-domain transfer method based on graph language alignment for graph-level anomaly detection. This framework integrates structure-aware graph encoders with instruction-aware text embeddings into a representation space constructed from multi-slice soft cosine objectives, and serializes local, global, and semantic attribute sequences into compact graph descriptors (GraphDP). The model utilizes Matroshka representations of slices to enforce multi-scale consistency to capture anomalies at different granularities, and performs density estimation on the alignment hypersphere using spherical multi-modal scoring (SMS). Experiments show that GLASS achieves better average AUROC rankings than recent advanced baselines in twelve benchmark tests and three meta-domains, and demonstrates effective cross-domain transfer detection capabilities.

Related eventsRELATED EVENTS
Key entitiesKEY ENTITIES
GLASS

Integrated timelineUNIFIED TIMELINE

  1. 2026-09-04

    GLASS: Graph-Language Alignment with Sp…

    GLASS 框架通过图语言对齐实现鲁棒的跨域迁移,在十二个基准和三个元域上获得最佳平均 AUROC 及排名。该框架将结构感知图编码器与指令感知文本嵌入统一于超球面表示空间,利用多切片软余弦目标构建紧凑的图描述符提示(GraphDP)。通过…

  2. 2026-09-07

    GLASS: Graph-Language Alignment with Sp…

    GLASS 框架通过图语言对齐在单位超球面上实现鲁棒的跨域迁移能力。该框架将结构感知图编码器与指令感知文本嵌入统一至多切片软余弦目标构建的表示空间,并将局部、全局及语义属性序列化为紧凑的图描述符提示(GraphDP)。模型利用马特罗什卡表…

SignalsSIGNALS

Keyword heat
  • GLASS2

All reports (2)SOURCES

A arXiv cs.LG en 2026-09-04 23:16

GLASS: Graph-Language Alignment with Spherical Scoring for Transferable Graph-Level Anomaly Detection

GLASS 框架通过图语言对齐实现鲁棒的跨域迁移,在十二个基准和三个元域上获得最佳平均 AUROC 及排名。该框架将结构感知图编码器与指令感知文本嵌入统一于超球面表示空间,利用多切片软余弦目标构建紧凑的图描述符提示(GraphDP)。通过强制多尺度一致性,模型捕捉不同粒度下的异常偏差;在评分方面,提出球形多模态评分(SMS),在图与文本嵌入空间中实例化冯·米塞斯 - 费舍尔核密度估计器。共享文本嵌入空间支持跨域桥接:无需目标域训练数据即可执行零样本异常检测,仅需少量正常样本即可通过参考集校准实现少样本适应。

A arXiv cs.LG en 2026-09-07 12:00

GLASS: Graph-Language Alignment with Spherical Scoring for Transferable Graph-Level Anomaly Detection

GLASS 框架通过图语言对齐在单位超球面上实现鲁棒的跨域迁移能力。该框架将结构感知图编码器与指令感知文本嵌入统一至多切片软余弦目标构建的表示空间,并将局部、全局及语义属性序列化为紧凑的图描述符提示(GraphDP)。模型利用马特罗什卡表示切片强制执行多尺度一致性以捕捉不同粒度异常,并在对齐超球面上通过球形多模态评分(SMS)进行密度估计。GLASS 在十二个基准测试和三个元领域中取得了优于近期先进基线的平均 AUROC 排名,并实现了有效的跨域迁移检测。