← Back to all news
arXiv Machine Learning By Yuxin Yang, Limei Hu, Feng Chen

DDGAD: Disagreement-Driven Graph Anomaly Detection via Adapt-Then-Combine

Read the original on arXiv Machine Learning →

DDGAD introduces a novel approach to graph anomaly detection that focuses on the disagreement between node-wise and contextual estimates rather than on their combined state. By adapting the Adapt-Then-Combine framework, DDGAD generates separate node-wise and neighborhood-dependent estimates, accumulating their pre-consensus disagreement across iterations to identify anomalies. The method is theoretically grounded with graph-spectral and source-response analyses, and empirical results on six benchmarks demonstrate superior AUROC performance compared to existing techniques.

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 AI
Sep 3

RINSE: Robust Target-Time Normality Estimation for Zero-Shot Graph Anomaly Detection

RINSE (Robust Iterative Normality Self-Estimation) is a gradient‑free framework for zero‑shot graph anomaly detection that keeps a source‑trained detector fixed while iteratively estimating target normality, calibrating representations, and assessing evidence reliability on unseen target graphs. It identifies a reliable subset of low‑residual target nodes to build a trimmed target‑aware normality model and fuses complementary anomaly evidence through reliability‑gated rank fusion and encoder ensembling. Across eight unseen target graphs, RINSE achieves the highest average AUPRC under two preprocessing protocols, with ablation and sensitivity analyses supporting its combined design.

By Taufikur Rahman Fuad, Md Abrar Jahin, Amir Hussain
More like this →