An autoML framework & toolkit for machine learning on graphs.

Implementation of Principal Neighbourhood Aggregation for Graph Neural Networks in PyTorch, DGL and PyTorch Geometric

The official implementation for ICLR23 spotlight paper "DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion"

A PyTorch implementation of "Signed Graph Convolutional Network" (ICDM 2018).

Implementation of MolCLR: "Molecular Contrastive Learning of Representations via Graph Neural Networks" in PyG.

[CVPR'22 Best Paper Finalist] Official PyTorch implementation of the method presented in "Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation"

GOOD: A Graph Out-of-Distribution Benchmark [NeurIPS 2022 Datasets and Benchmarks]

Implementation of "GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings" in PyTorch

Making self-supervised learning work on molecules by using their 3D geometry to pre-train GNNs. Implemented in DGL and Pytorch Geometric.

PyTorch Geometric Signed Directed is a signed/directed graph neural network extension library for PyTorch Geometric. The paper is accepted by LoG 2023.

Topological Graph Neural Networks (ICLR 2022)

Code for SIGGRAPH paper CNNs on Surfaces using Rotation-Equivariant Features

A graph reliability toolbox based on PyTorch and PyTorch Geometric (PyG).

The official implementation for ICLR23 paper "GNNSafe: Energy-based Out-of-Distribution Detection for Graph Neural Networks"

Given an input graph (ArangoDB or PyG) it generates graph embeddings using Low-Code framework built on top of PyG.

Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection (ECCV 2022)

A PyTorch Geometric implementation of SimGNN with some extensions.

GraphCON (ICML 2022)

Official PyTorch Implementation of "Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs". NeurIPS 2020.

Gradient gating (ICLR 2023)