Yinghong Shi

Abstract Financial fraud detection requires screening massive transaction networks where evolving topologies, extreme label sparsity, and asymmetric misclassification costs make traditional classification paradigms ineffective. We propose ST-CGNN, a spatio-temporal contrastive graph neural network that frames operational screening as a multi-task learning problem in which a shared encoder is supervised by a contrastive regularizer and an evidential triage head.

4. Discussion Compared to visible imaging, NIR-II fluorescence imaging has demonstrated many advantages, such as much reduced light scattering, diminished autofluorescence background, and enhanced tissue penetration [,]. When NIR-II fluorescence technique was devised at its infancy, only a handful of imaging dyes were available [,].