HIGHLIGHTS
- What: CuGNN`s feature-distribution embedding and latent-space contrastive learning strategies are utilized to detect anomalous interactions in high-frequency trading networks and to identify heterophilic relationships in credit scoring and supply chain By applying the CuGNN framework across diverse financial datasets this study shows its potential to uncover hidden structures and optimize decision-making in critical financial applications addressing the growing need for explainable and adaptive graph-based methods in the sector.
- Who: SOONG CHINGTSING from the Financial System Research Centre, Canada have published the paper: Contrastive Unsupervised Graph Neural Network in Financial . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.