lightgcn

This is our implementation of ENMF: Efficient Neural Matrix Factorization (TOIS. 38, 2020). This also provides a fair evaluation of existing state-of-the-art recommendation models.

The code repository for the paper: Peijie et al., Neighborhood-Enhanced Supervised Contrastive Learning for Collaborative Filtering. IEEE TKDE, 2023.

用pytorch 方法复现了二十多个经典的推荐算法论文，其中包含排序论文和推荐召回论文，并在demo里面选了一个召回模型和排序模型的运行示例。

Source code for the RecSys 2024 paper "Revisiting LightGCN: Unexpected Inflexibility, Inconsistency, and A Remedy Towards Improved Recommendation."

Source code for the ICML 2026 paper "Rethinking Contrastive Learning in Graph Collaborative Filtering: Limitations and A Simple Remedy"

rusket 🦀🧺

🧴 妆策AI 面向美妆新零售实战场景的智能推荐与营销转化平台 | AI-powered Beauty New Retail Platform | 15+ Algorithms | GBDT AUC=0.9993 | LightGCN HR@10=0.8413 | Six-Dimension Scoring

RecSys Codes based on PyTorch

A Recommender System for Google Maps reviews using LightGCN.

CartWise 是一个基于 FastAPI + Streamlit 的乐器电商自然语言推荐系统

Graph-based movie recommendation system using ItemKNN, MF-BPR, LightGCN, and GraphSAGE on the MovieLens 20M dataset.

GNN-based movie recommendation system using LightGCN on MovieLens 100K, with anomaly detection

Two-Tower RecSys + FAISS retrieval + cold-start demo (Amazon Video Games 2023)

GNN-based recommendation under extreme data sparsity for WuxiaWorld web serials

基于 LightGCN 与 BPR 的用户兴趣建模和答案推荐实验

A sample pipeline that generates graph-based Embeddings for a graph and uses them to predict potential drug-disease associations

Here is my implementation of a recommendation system using gated lightgcn and transact.

"GNN(LightGCN) 기반 Long-tail 추천 시스템 | Tail-aware Sampling(DC/BC) | AWS SageMaker HPO | PyTorch"

This repository documents our comprehensive approach to building an effective recommendation system for predicting customer repurchases on Carrefour's eCommerce platform. Starting with simple statistical methods and progressing to advanced neural network architectures, we've explored multiple approaches to tackle this recommendation challenge.

GNN 召回 + 强化学习重排的个性化推荐系统：LightGCN 二部图召回、Policy Gradient 多样性重排、三随机种子离线评测（Recall/NDCG/Coverage/Diversity）与 FastAPI/Docker/CI 服务闭环。 | GNN retrieval with RL reranking: LightGCN bipartite-graph candidate generation, policy-gradient diversity reranking, multi-seed offline evaluation and a served FastAPI/Docker pipeline.