Skip to content
#

gcn-architecture

Here are 18 public repositories matching this topic...

Evaluation of multiple graph neural network models—GCN, GAT, GraphSAGE, MPNN and DGI—for node classification on graph-structured data. Preprocessing includes feature normalization and adjacency-matrix regularization, and an ensemble of model predictions boosts performance. The best ensemble achieves 83.47% test accuracy.

  • Updated May 12, 2025
  • Jupyter Notebook

This project implements a Variational Autoencoder (VAE) for generating valid drug-like molecules using the ZINC dataset. It leverages Relational Graph Convolutional Networks (R-GCN) for the encoder and a dense network for the decoder, capable of transforming SMILES strings into molecular graphs and generating new molecules from the latent space.

  • Updated Dec 12, 2025
  • Jupyter Notebook

Improve this page

Add a description, image, and links to the gcn-architecture topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the gcn-architecture topic, visit your repo's landing page and select "manage topics."

Learn more