PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models (CIKM 2021)

TensorFlow GNN is a library to build Graph Neural Networks on the TensorFlow platform.

A PyTorch implementation of "Capsule Graph Neural Network" (ICLR 2019).

Implementation and experiments of graph neural netwokrs, like gcn,graphsage,gat,etc.

A PyTorch implementation of "SimGNN: A Neural Network Approach to Fast Graph Similarity Computation" (WSDM 2019).

The PyTorch implementation of STGCN.

Transform geospatial relations into graphs for GNNs and spatial network analysis

Code and resources on scalable and efficient Graph Neural Networks (TNNLS 2023)

Efficient and Friendly Graph Neural Network Library for TensorFlow 1.x and 2.x

PyTorch implementation of MTAD-GAT (Multivariate Time-Series Anomaly Detection via Graph Attention Networks) by Zhao et. al (2020, https://arxiv.org/abs/2009.02040).

A PyTorch Graph Neural Network Library

tsl: a PyTorch library for processing spatiotemporal data.

[NeurIPS'22] Tokenized Graph Transformer (TokenGT), in PyTorch

1. Use BERT, ALBERT and GPT2 as tensorflow2.0's layer. 2. Implement GCN, GAN, GIN and GraphSAGE based on message passing.

[TKDD 2023] Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution

PyTorch implementation of Graph Matching Networks, e.g., Graph Matching with Bi-level Noisy Correspondence (COMMON, ICCV 2023), Graph Matching Networks for Learning the Similarity of Graph Structured Objects (GMN, ICML 2019).

Code for "Graph Neural Network on Electronic Health Records for Predicting Alzheimer’s Disease"

Source code for GNN-LSPE (Graph Neural Networks with Learnable Structural and Positional Representations), ICLR 2022

The unravelsports package aims to aid researchers, analysts and enthusiasts by providing intermediary steps in the complex process of turning raw sports data into meaningful information and actionable insights.

GemNet model in PyTorch, as proposed in "GemNet: Universal Directional Graph Neural Networks for Molecules" (NeurIPS 2021)