This repository is a curated list of academic resources on hypergraph learning, theory, datasets, and tools. It serves researchers and practitioners interested in leveraging hypergraphs for complex relational data analysis, offering a comprehensive overview of state-of-the-art methods and applications.

How It Works

The project compiles research papers, datasets, and software libraries related to hypergraph learning. It covers various theoretical aspects, algorithmic approaches (e.g., hypergraph neural networks, spectral methods), and practical applications across domains like recommendation systems, computer vision, and social network analysis. The curated nature aims to provide a structured entry point into this specialized field.

Quick Start & Requirements

This is a curated list, not a runnable software package. To utilize the listed tools and datasets:

• PyTorch Geometric: For Hypergraph Convolutional Networks. PyTorch Geometric Docs
• DeepHypergraph: For Hypergraph Neural Networks. DeepHypergraph GitHub
• OpenHGNN: For Heterogeneous Graph Neural Networks. OpenHGNN GitHub
• KaHyPar: For Hypergraph Partitioning. KaHyPar GitHub
• Datasets: Links to specific datasets (e.g., Cora, Citeseer, Pubmed) are provided within the README.

Highlighted Details

• Extensive coverage of recent conference papers (ICML, NeurIPS, ICLR, KDD, SIGIR, WWW, AAAI, IJCAI, CIKM, ICDM, TPAMI, TKDE, TIP, TNNLS, TCYB, TMM, FOCS, SODA, STOC, COLT, ESA, JACM, TIT) and journal articles.
• Includes a variety of benchmark datasets for hypergraph node classification and clustering tasks.
• Lists several open-source tools and libraries for hypergraph analysis, including PyTorch Geometric, DeepHypergraph, OpenHGNN, and HyperNetX.

Maintenance & Community

The repository is maintained by gzcsudo. It appears to be a static compilation of resources, with no explicit mention of active community channels, roadmaps, or ongoing development efforts beyond the initial curation.

Licensing & Compatibility

The repository itself is a list of links and does not have a specific license. The licenses of the linked tools and datasets would need to be checked individually. Compatibility for commercial use depends entirely on the licenses of the referenced software and data.

Limitations & Caveats

This repository is a collection of pointers to external resources and does not provide any executable code or unified framework. Users must individually assess and integrate the listed tools and datasets. The rapid evolution of the field means some listed resources may become outdated.