SAGE-FIN, a semi-supervised graph autoencoder with a classification head, detects fraudulent Bitcoin nodes on Elliptic++ and explains flags by measuring loss changes when edges are removed.
IEEE (page 188-194) (2016)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-fin.ST 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Detecting Fraud in Financial Networks: A Semi-Supervised GNN Approach with Granger-Causal Explanations
SAGE-FIN, a semi-supervised graph autoencoder with a classification head, detects fraudulent Bitcoin nodes on Elliptic++ and explains flags by measuring loss changes when edges are removed.