SGNN-IB combines edge-type graph splitting, Beta-wavelet spectral filters, prototype-based frequency fusion, and an information-bottleneck-style regularizer to improve fraud detection on YelpChi, Amazon, and FDCompCN.
Sefraud: Graph-based self- explainable fraud detection via interpretative mask learning,
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
-
Addressing Noise and Stochasticity in Fraud Detection for Service Networks
SGNN-IB combines edge-type graph splitting, Beta-wavelet spectral filters, prototype-based frequency fusion, and an information-bottleneck-style regularizer to improve fraud detection on YelpChi, Amazon, and FDCompCN.