# PaddlePaddle/PGL

Paddle Graph Learning (PGL) is an efficient and flexible graph learning framework based on PaddlePaddle

Repository: https://github.com/PaddlePaddle/PGL
Canonical: https://ross.abutalabs.com/products/pgl
Language: Python
License: Apache-2.0
License Family: permissive
Topics: heterogeneous-graph-learning, graph-neural-network, graph, metapath, graph-learning
Last push: 2023-12-11T05:15:14+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2640, "days_push": 996, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1585, forks 309 (observed 2026-08-28T04:05:07.549468+00:00)

## What it is
Paddle Graph Learning (PGL) is an efficient and flexible graph learning framework built on PaddlePaddle. It supports heterogeneous graph learning, message-passing GNNs, distributed graph engines, and large-scale graph training for tasks like recommendation and knowledge graph embeddings.

## Use cases
- train graph neural networks on large graphs
- learn embeddings for heterogeneous graphs with metapaths
- build recommender systems with graph neural networks
- train knowledge graph embeddings at scale
- run distributed graph learning on massive datasets
- reproduce OGB benchmark competition solutions

## When to choose
- you are already using the PaddlePaddle ecosystem
- you need heterogeneous graph learning with metapath support
- you need to scale GNN training to very large graphs or distributed settings

## When to avoid
- your stack is PyTorch-based (consider PyG or DGL instead)
- you need a framework with frequent recent updates
- you only need simple graph analytics without deep learning

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning, graph-processing
- platform: python
- tags: graph-neural-networks, heterogeneous-graphs, paddlepaddle, graph-learning, knowledge-graphs, linux, gpu

## Member repositories
- PaddlePaddle/PGL (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:07.549468+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 2026-08-30T03:55:31.265823+00:00, confidence not recorded.
  - readme: https://github.com/PaddlePaddle/PGL (fetched 2026-08-28T04:05:07.549468+00:00, sha d0d986206f1f)
  - registry_pypi: https://pypi.org/pypi/pgl/json (fetched 2026-08-29T11:26:09.569381+00:00, sha 77de2c670352)
- Data as of 2026-08-30T08:39:29.467469+00:00.