ProTAGAD separates text and graph-structure anomaly evidence into two prototype banks and reports state-of-the-art zero-shot results on eight synthetic text-attributed graph targets.
International conference on machine learning , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ProTAGAD: A Foundation Model for TAG Anomaly Detection with Decoupled Topological and Textual Prototypes
ProTAGAD separates text and graph-structure anomaly evidence into two prototype banks and reports state-of-the-art zero-shot results on eight synthetic text-attributed graph targets.