Graph Convolutional Network
Graph Convolutional Networks (GCNs) are a type of neural network designed to analyze data represented as graphs, focusing on learning relationships between interconnected nodes. Current research emphasizes improving GCN performance through techniques like graph pruning, transfer learning, and incorporating diverse data modalities (e.g., multi-omics, spatio-temporal data) into model architectures such as variational mode decomposition and dual graph convolutional networks. GCNs find broad application in diverse fields, including traffic prediction, drug response prediction, and disease diagnosis, offering powerful tools for analyzing complex relational data and extracting meaningful insights.
Papers
ICDBigBird: A Contextual Embedding Model for ICD Code Classification
George Michalopoulos, Michal Malyska, Nicola Sahar, Alexander Wong, Helen Chen
Domain Invariant Model with Graph Convolutional Network for Mammogram Classification
Churan Wang, Jing Li, Xinwei Sun, Fandong Zhang, Yizhou Yu, Yizhou Wang