A bi-directional curriculum module that trains two copies of any graph anomaly detector on opposite difficulty orderings and fuses their scores improves detection on seven benchmarks.
Sheng, Hui Xiong, and Le- man Akoglu
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity
A bi-directional curriculum module that trains two copies of any graph anomaly detector on opposite difficulty orderings and fuses their scores improves detection on seven benchmarks.