Hypergraph Neural Networks (AAAI 2019)

Python package for hypergraph analysis and visualization.

EasyGraph is an open-source network analysis library designed to cover advanced network processing methods. It includes functionalities for detecting structural hole spanners, network embedding, and various classic network analysis techniques.

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

NeurIPS 2019: HyperGCN: A New Method of Training Graph Convolutional Networks on Hypergraphs

Implementation of EMNLP2020 -- Be More with Less: Hypergraph Attention Networks for Inductive Text Classification

The source code of IEEE TPAMI 2025 "Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation".

HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation

[NeurIPS'21] Higher-order Transformers for sets, graphs, and hypergraphs, in PyTorch

[WWW'21] Multiplex Bipartite Network Embedding using Dual Hypergraph Convolutional Networks

Code for Spatiotemporal Hypergraph Convolution Network for Stock Movement Forecasting

The source code of ICLR 2025 "Beyond Graphs: Can Large Language Models Comprehend Hypergraphs?"

[ECCV'22] Equivariant Hypergraph Neural Networks, in PyTorch

Hypergraph Database.

multiway chromatin interaction, 3D genome, single-nucleus, hypergraph representation learning

[NeurIPS 2024] Official resources of "Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary relational Knowledge Graph Construction".

Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning

[AAAI 2023] Official resources of "DHGE: Dual-view Hyper-Relational Knowledge Graph Embedding for Link Prediction and Entity Typing".

Standardized higher-order datasets with corresponding datasheets

A simple python package for graph theory that supports multi-edges, hyper-edges, looped-edges and every other combination of these.