IEEE

UPN-GCN: Update Positive-Negative Graph Convolution Neural Network in Non-Euclidean Structured Data

Abstract: Graph Convolutional neural Networks (GCNs) demonstrate exceptional effectiveness when working with data that have non-Euclidean structures. In recent years, numerous researchers have ...
National Bureau of Economic Research

Externalities and the Taxation of Top Earners

This paper characterizes the optimal taxation of top earners in a world with externalities. It takes a reduced-form approach that spans a broad class of models where top earners create externalities ...
IEEE

False Negative Sample Detection for Graph Contrastive Learning

Abstract: Recently, self-supervised learning has shown great potential in Graph Neural Networks (GNNs) through contrastive learning, which aims to learn discriminative features for each node without ...
Frontiers

KG2ML: Integrating Knowledge Graphs and Positive Unlabeled Learning for Identifying Disease-Associated Genes

The final, formatted version of the article will be published soon. Background Biomedical knowledge graphs (KGs), such as the Data Distillery Knowledge Graph (DDKG), capture known relationships among ...