PaddlePaddle/PGL

Health v2 · maintenance only

Adoption not part of the score

1585 stars · 309 forks observed · 2026-08-28

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

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

library · maturity maintenance

machine-learning deep-learning machine-learning deep-learning graph-processing python graph-neural-networks heterogeneous-graphs paddlepaddle graph-learning knowledge-graphs linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="PaddlePaddle/PGL")