Your PyTorch AI Factory - Flash enables you to easily configure and run complex AI recipes for over 15 tasks across 7 data domains

Bag of Tricks for Graph Neural Networks.

Bags of Tricks in OGB (node classification) with GCNs.

GCA-ROM is a library which implements graph convolutional autoencoder architecture as a nonlinear model order reduction strategy.

Code repo for the paper "AIO-P: Expanding Neural Performance Predictors Beyond Image Classification", accepted to AAAI-23.

g2-MLP: State-of-the-Art Model for Node Classification on Graphs (PPI Dataset)

Code repo for the paper "GENNAPE: Towards Generalized Neural Architecture Performance Estimators", accepted to AAAI-23.

Project for Deep Learning And Applied AI course at the University of "La Sapienza" in Master in Computer Science A.A. 2021/2022

This repository is a brief tutorial about how Graph convolutional networks and message passing networks work with example code demonstration using pytorch and torch_geometric

🧬 Official implementation of Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks [ICML 2024]

In this repo I have implement different applications of GNN which covers Node Level, Edge level, Graph level tasks with different GNN variants such as GCN, GAT, Graph SAGE

Forecast NYC taxi activity with deep learning. We compare the performances of models based on MLPs, RNNs, LSTMs, GNNs, and ARIMAX. Additionally, our code provides users with an easy-to-use pipeline for producing custom time series datasets of taxi activity from publicly available NYC TLC data.

Torch geometric compatible node embedders

PyTorch code for an effective way of making a Molecular Graph Dataset in Torch Geometric involving a pair of graphs from chemical SMILE strings

Tools for querying, visualizing, and modeling network graphs on the Helium blockchain.

An introduction to graph neural networks with pytorch

using GA to find an important subgraph

This project optimizes a Graph Convolutional Network (GCN) model with Optuna to predict COVID-19 cases in various regions, incorporating additional features alongside historical data for improved accuracy.

Rebased the code for GPPT

Graph Convolution Network aided Sentiment Analysis with Dependencies utilisation