← Back to all news
arXiv Machine Learning By Xudong Wang, Chris Ding, Tongxin Li, Jicong Fan

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

Read the original on arXiv Machine Learning →

GLASS is a graph‑level anomaly detection framework that aligns graph and language representations on a unit hypersphere to achieve cross‑domain transferability. It constructs a Graph Descriptor Prompt to encode local, global, and semantic graph properties, and uses a multi‑slice soft cosine objective to unify graph and text embeddings. Anomaly scoring is performed via spherical density estimation with von Mises‑Fisher kernels, enabling zero‑shot detection and few‑shot adaptation across twelve benchmarks and three meta‑domains, outperforming recent GLAD baselines.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Oct 23

One Pretrained Decision Model Is Enough for Training-Free Generalist Graph Anomaly Detection

The paper introduces Jev-GAD, a training‑free generalist graph anomaly detection framework that combines complementary structural, attribute, and neighborhood evidence with a single frozen pretrained language model for anomaly assessment. It transforms heterogeneous statistics into graph‑relative percentiles and uses a semantic Graph‑to‑State (G2S) transformation to feed evidence into a non‑generative decision readout, fusing the resulting scores with four statistical measures. Experiments on seven benchmark datasets show Jev‑GAD achieving high AUROC (89.18%) and AUPRC (52.40%) scores, demonstrating the effectiveness of pretrained decision readout and semantic evidence grounding.

By Xinyu Zhao, Qingyun Sun, Ziwei Zhang, Tianchen Zhu, Daqing Li, Jianxin Li
llmsbenchmarks
More like this →
arXiv Machine Learning
Sep 23

Can We Predict Anomaly Detection Performance from Embedding-Space Geometry?

The paper investigates whether the performance of anomaly detection systems can be predicted without labeled anomalies. For kNN-based detectors, it derives a lower bound on AUC that links detection performance to the separation and variance of inlier and outlier scores, and uses this to analyze how density variation, intrinsic dimensionality, and domain mismatch affect score variability. The authors introduce pseudo‑anomaly probes that provide a reference for estimating relative score separation, and demonstrate through experiments on DCASE benchmarks that these probes enable anomaly‑free model selection to outperform conventional development‑set selection, especially under domain shift.

By Kevin Wilkinghoff, Zheng-Hua Tan
ragbenchmarks
More like this →
arXiv AI
Aug 12

ProTAGAD: A Foundation Model for TAG Anomaly Detection with Decoupled Topological and Textual Prototypes

arXiv:2608. 10699v1 Announce Type: cross Abstract: Text-Attributed Graphs (TAGs), endowed with abundant textual content along with topological structures, have emerged as a versatile backbone for real-world anomaly detection spanning large language model security, social network moderation, and cyber threat identification.

By Ziyan Wang, Liwen Wu, Cheng Xie, Song Gao, Zhenli He, Xin Jin
llmsbenchmarks
More like this →
arXiv Machine Learning
Sep 17

FoundAna: A GNN-assisted Foundation Model for Graph Anomaly Detection

FoundAna is a GNN‑assisted foundation model designed for graph anomaly detection across diverse datasets. It combines a GNN component with a transformer encoder enhanced by four positional encodings to capture both local and global structure, using reconstruction errors as anomaly scores. Experiments on nine benchmark datasets from financial, social, and citation networks show that FoundAna consistently outperforms state‑of‑the‑art baselines.

By Suprim Nakarmi, Chahana Dahal, Yue Zhao, Junggab Son, Zuobin Xiong
llmsbenchmarks
More like this →