Projects sharing features with SimGNN

A PyTorch implementation of "Graph Classification Using Structural Attention" (KDD 2018).

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

An implementation of "MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing" (ICML 2019).

The official PyTorch implementation of "Pathfinder Discovery Networks for Neural Message Passing" (WebConf '21)

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

A PyTorch implementation of "Semi-Supervised Graph Classification: A Hierarchical Graph Perspective" (WWW 2019)

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

A PyTorch Implementation of "SINE: Scalable Incomplete Network Embedding" (ICDM 2018).

A Pytorch implementation of "Splitter: Learning Node Representations that Capture Multiple Social Contexts" (WWW 2019).

Generate embeddings from large-scale graph-structured data.

Hypernetwork Knowledge Graph Embeddings

TuckER: Tensor Factorization for Knowledge Graph Completion

Official PyTorch Implementation of SAGPool - ICML 2019

Position-aware Graph Neural Networks

MagNet graph convolutional network

🤖 A Python library for learning and evaluating knowledge graph embeddings

PyTorch Geometric is a library for building and training machine learning models on graph-structured data. It provides a framework for developing graph neural networks, including a specialized system for implementing node-to-node information exchange via customizable message passing, aggregation, and update functions. The library includes a sparse data processing toolkit that utilizes accelerated CPU and CUDA kernels to perform efficient reductions on large sparse datasets. It supports the creation of specialized architectures for structured data such as 3D meshes and point clouds. The proje

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

Official code for the SDM2022 paper -- SSSNET: Semi-Supervised Signed Network Clustering.

Embed arbitrary graphs in Hyperbolic space