Get Started
Research questionHow can zero-shot graph anomaly detectors remain reliable on unlabeled targets under domain shift?Domain shift can make the source graph’s notion of normality unreliable on a new target graph, causing normal target nodes to be flagged as anomalous.
AI
Machine Learning
Statistical Machine Learning
Latest papersRecent research connected to this question, newest first.RINSE: Robust Target-Time Normality Estimation for Zero-Shot Graph Anomaly DetectionThe study evaluates a fixed source-trained detector with gradient-free target-time adaptation across eight unseen target graphs, reporting AUPRC under two preprocessing protocols. The evidence concerns the supplied graph anomaly detection setting and does not establish performance beyond the evaluated targets.research paper · Sep 2, 2026
Related questions
How can graph-level anomaly detection transfer to new domains with little or no target data?How can object detectors trained on uncamouflaged imagery generalize to unseen camouflage with little target-domain data?How can detect-to-track pipelines adapt to new visual domains without target-domain labels?How can AI-generated text detectors remain reliable under distribution shift?
Home
Topics
Search
Library