# Jhy1993/HAN

Heterogeneous Graph Neural Network

Repository: https://github.com/Jhy1993/HAN
Canonical: https://ross.abutalabs.com/products/jhy1993-han
Language: Python
License Family: other
Topics: graph-neural-network, network-embedding, graph-attention-network, heterogeneous-network, heterogeneous-graph, heterogeneous-graph-neural-network
Last push: 2020-05-06T15:46:06+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2764, "days_push": 2310, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1219, forks 225 (observed 2026-08-28T04:04:01.778052+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: machine-learning, data-science
- platform: python
- tags: graph-neural-network, heterogeneous-graph, graph-attention-network, network-embedding, research-code, www-2019, algorithms

## Member repositories
- Jhy1993/HAN (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:01.778052+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:16:11.345641+00:00, confidence not recorded.
  - readme: https://github.com/Jhy1993/HAN (fetched 2026-08-28T04:04:01.778052+00:00, sha 1f322ac35045)
- Data as of 2026-08-30T08:39:29.467469+00:00.