gusye1234/LightGCN-PyTorch

Health v2 · maintenance only

Flags: no_releases archived no_license

Adoption not part of the score

1072 stars · 294 forks observed · 2026-08-28

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

A PyTorch implementation of LightGCN, a simplified graph convolution network for collaborative filtering recommendation from the SIGIR 2020 paper. It includes processed datasets (Gowalla, Yelp2018, Amazon-book, LastFM) and training/evaluation scripts.

Use cases

• reproduce LightGCN recommendation results
• train a graph convolution recommender on my own dataset
• compare collaborative filtering models like BPR and LightGCN
• learn how GCN-based recommendation works
• benchmark recall and ndcg on Gowalla Yelp2018 Amazon-book

When to choose

• you need a faithful PyTorch reimplementation of the LightGCN paper
• you want a simple GCN baseline for collaborative filtering research
• you want ready-processed recommendation benchmark datasets

When to avoid

• you need a production recommender system with serving infrastructure
• you need a maintained library with a license and long-term support
• you want a general-purpose GNN framework rather than a specific model

Facets

library · maturity maintenance

machine-learning deep-learning machine-learning deep-learning python lightgcn graph-convolutional-network collaborative-filtering recommender-system pytorch research-code recommendation

Member repositories

For agents

markdown · JSON · MCP: product_card(name="gusye1234/LightGCN-PyTorch")