GitHub

Spatio-Temporal Graph Convolutional Networks:

We propose a novel deep learning framework, STGCN, to tackle time series prediction problem in traffic domain. Instead of applying regular convolutional and recurrent units, we formulate the problem ...
IEEE

Kolmogorov-Arnold Networks for Graph Isomorphism and Complex Representation

This study proposes KGI, a novel graph isomorphism network that integrates Kolmogorov-Arnold Networks (KAN) into graph representation learning. Unlike traditional Graph Isomorphism Networks (GIN) that ...
GitHub

graph-isomorphism-networks

Melty Molecule is a molecular property prediction system that leverages graph neural networks to predict melting points of chemical compounds. The model uses a hybrid architecture combining Principal ...
IEEE

Leveraging High Dimensional Spatial Graph Embedding as a Heuristic for Graph Algorithms

Abstract: Spatial graph embedding is a technique for placing graphs in space used for visualization and graph analytics. The general goal is to place connected nodes close together while spreading ...
Frontiers

Multimodal graph neural networks in healthcare: a review of fusion strategies across biomedical domains

1 Department of Analytics, Harrisburg University of Science and Technology, Harrisburg, PA, United States 2 Department of Emergency Medicine, UMass Chan Medical School, Worcester, MA, United States ...