Jhy1993/HAN

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1219 stars · 225 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Reference implementation of the Heterogeneous Graph Attention Network (HAN) model from the WWW 2019 paper, built on top of GAT in Python. It includes preprocessing scripts and datasets (DBLP, ACM) for node classification and network embedding on heterogeneous graphs.

Use cases

• run heterogeneous graph attention network experiments
• node classification on heterogeneous graphs like DBLP and ACM
• learn graph neural network embeddings for multi-type node graphs
• reproduce HAN paper results
• compare GNN baselines like GCN and GAT on meta-path graphs

When to choose

• you need the official HAN model implementation for research or benchmarking
• you work with heterogeneous graphs and meta-path based attention
• you want preprocessed DBLP/ACM datasets for GNN experiments

When to avoid

• you need a maintained production library with a license and active support
• you want homogeneous graph neural networks only
• you need inductive learning on unseen graphs - the authors note suitable datasets are lacking

Facets

library · maturity maintenance

machine-learning deep-learning machine-learning data-science python graph-neural-network heterogeneous-graph graph-attention-network network-embedding research-code www-2019 algorithms

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Jhy1993/HAN")