Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
TRACK: Multiple Instance Learning for Anti-Money Laundering in Transaction Networks
Seonkyu Lim, Inwoo Tae, Gwangui Hong +5
Anti-money laundering (AML) investigations are organized around accounts, while the suspicious evidence for an account may reside in only a few of its transactions. Yet many accoun…
cs.LG2026
HoTS: Homophily-Aware Temperature Scaling for Graph Neural Network Calibration
Inwoo Tae, Yoontae Hwang, Yongjae Lee
For graph node classification, calibrated class probabilities are needed when confidence scores, usually the maximum predicted class probability, are used to rank predictions, defe…