Description
LightGCN is a type of graph convolutional neural network (GCN), including only the most essential component in GCN (neighborhood aggregation) for collaborative filtering. Specifically, LightGCN learns user and item embeddings by linearly propagating them on the user-item interaction graph, and uses the weighted sum of the embeddings learned at all layers as the final embedding.
Papers Using This Method
Improvement Graph Convolution Collaborative Filtering with Weighted addition input2025-03-27Rolling Forward: Enhancing LightGCN with Causal Graph Convolution for Credit Bond Recommendation2025-03-18Hypergraph Diffusion for High-Order Recommender Systems2025-01-28Graph Neural Controlled Differential Equations For Collaborative Filtering2025-01-23Position-aware Graph Transformer for Recommendation2024-12-25A Novel Evaluation Perspective on GNNs-based Recommender Systems through the Topology of the User-Item Graph2024-08-21Bundle Recommendation with Item-level Causation-enhanced Multi-view Learning2024-08-13SimCE: Simplifying Cross-Entropy Loss for Collaborative Filtering2024-06-23Balancing Embedding Spectrum for Recommendation2024-06-17Wasserstein Dependent Graph Attention Network for Collaborative Filtering with Uncertainty2024-04-09LightGCN: Evaluated and Enhanced2023-12-17VM-Rec: A Variational Mapping Approach for Cold-start User Recommendation2023-11-02A Topology-aware Analysis of Graph Collaborative Filtering2023-08-21Toward a Better Understanding of Loss Functions for Collaborative Filtering2023-08-11Challenging the Myth of Graph Collaborative Filtering: a Reasoned and Reproducibility-driven Analysis2023-08-01GNN4FR: A Lossless GNN-based Federated Recommendation Framework2023-07-25How Graph Convolutions Amplify Popularity Bias for Recommendation?2023-05-24Retraining A Graph-based Recommender with Interests Disentanglement2023-05-05Towards Explainable Collaborative Filtering with Taste Clusters Learning2023-04-27Dual Policy Learning for Aggregation Optimization in Graph Neural Network-based Recommender Systems2023-02-21