Abstract: Dear Editor, This letter presents a novel graph neural network, namely modularized graph convolution network (MGCN), to address the underexplored issue in graph convolution networks (GCNs), ...

Abstract: A dynamic graph (DG) is commonly encountered in many big data-related application scenarios, like cryptocurrency transaction analysis. A dynamic graph convolutional network (GCN) can ...

Decoding emotional states from electroencephalography (EEG) signals is a fundamental goal in affective neuroscience. This endeavor requires accurately modeling the complex spatio-temporal dynamics of ...

This repository contain Python scripts and Jupyter notebooks to (1) pretrain the graph state encoder used in the paper, and (2) run the cluster analysis and action prediction experiments contained in ...

Accurate prediction of protein-protein interactions (PPIs) is crucial for understanding cellular functions and advancing the development of drugs. While existing in-silico methods leverage direct ...

Department of Chemistry and Research Institute for Natural Science, Korea University, Seoul 02841, Korea ...

ABSTRACT: Convolutional auto-encoders have shown their remarkable performance in stacking deep convolutional neural networks for classifying image data during the past several years. However, they are ...

With the basic structure and parameters of the model remaining unchanged, this section analyzes and compares two types of network structures with input image sizes of 128 × 128 and 256 × 256. The ...