{"url":"/method/lightgcn","slug":"lightgcn","name":"LightGCN","full_name":"LightGCN","full_name_withheld":false,"description_markdown":"**LightGCN** is a type of [graph convolutional neural network](https://paperswithcode.com/method/gcn) (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.","description_state":"present","introduced_year":null,"introduced_by":{"title":"LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation","paper":"/paper/lightgcn-simplifying-and-powering-graph","first_author":"Xiangnan He","n_authors":6,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/lightgcn-simplifying-and-powering-graph"},"source":{"url":"https://arxiv.org/abs/2002.02126v4","title":"LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Graphs","area_id":"graphs","collection":"Graph Models","url":"/methods/category/graph-models","pwc_aliases":[]},{"area":"General","area_id":"general","collection":"Recommendation Systems","url":"/methods/category/recommendation-systems","pwc_aliases":[]}],"n_papers_tagged":46,"archive_num_papers":46,"papers_newest_first":[{"paper":"/paper/improvement-graph-convolution-collaborative","title":"Improvement Graph Convolution Collaborative Filtering with Weighted addition input","date":"2025-03-27","arxiv_id":"2503.21468","n_code_links":1,"syntology":null},{"paper":null,"title":"Rolling Forward: Enhancing LightGCN with Causal Graph Convolution for Credit Bond Recommendation","date":"2025-03-18","arxiv_id":"2503.14213","n_code_links":0,"syntology":null},{"paper":null,"title":"Hypergraph Diffusion for High-Order Recommender Systems","date":"2025-01-28","arxiv_id":"2501.16722","n_code_links":0,"syntology":null},{"paper":"/paper/graph-neural-controlled-differential-1","title":"Graph Neural Controlled Differential Equations For Collaborative Filtering","date":"2025-01-23","arxiv_id":"2501.13908","n_code_links":1,"syntology":null},{"paper":null,"title":"Position-aware Graph Transformer for Recommendation","date":"2024-12-25","arxiv_id":"2412.18731","n_code_links":0,"syntology":null},{"paper":"/paper/a-novel-evaluation-perspective-on-gnns-based","title":"A Novel Evaluation Perspective on GNNs-based Recommender Systems through the Topology of the User-Item Graph","date":"2024-08-21","arxiv_id":"2408.11762","n_code_links":1,"syntology":null},{"paper":"/paper/bundle-recommendation-with-item-level","title":"Bundle Recommendation with Item-level Causation-enhanced Multi-view Learning","date":"2024-08-13","arxiv_id":"2408.08906","n_code_links":1,"syntology":null},{"paper":"/paper/simce-simplifying-cross-entropy-loss-for","title":"SimCE: Simplifying Cross-Entropy Loss for Collaborative Filtering","date":"2024-06-23","arxiv_id":"2406.16170","n_code_links":1,"syntology":null},{"paper":"/paper/balancing-embedding-spectrum-for","title":"Balancing Embedding Spectrum for Recommendation","date":"2024-06-17","arxiv_id":"2406.12032","n_code_links":1,"syntology":null},{"paper":null,"title":"Wasserstein Dependent Graph Attention Network for Collaborative Filtering with Uncertainty","date":"2024-04-09","arxiv_id":"2404.05962","n_code_links":0,"syntology":null},{"paper":"/paper/lightgcn-evaluated-and-enhanced","title":"LightGCN: Evaluated and Enhanced","date":"2023-12-17","arxiv_id":"2312.16183","n_code_links":1,"syntology":null},{"paper":"/paper/vm-rec-a-variational-mapping-approach-for","title":"VM-Rec: A Variational Mapping Approach for Cold-start User Recommendation","date":"2023-11-02","arxiv_id":"2311.01304","n_code_links":1,"syntology":null},{"paper":"/paper/a-topology-aware-analysis-of-graph","title":"A Topology-aware Analysis of Graph Collaborative Filtering","date":"2023-08-21","arxiv_id":"2308.10778","n_code_links":1,"syntology":null},{"paper":"/paper/toward-a-better-understanding-of-loss","title":"Toward a Better Understanding of Loss Functions for Collaborative Filtering","date":"2023-08-11","arxiv_id":"2308.06091","n_code_links":1,"syntology":null},{"paper":"/paper/challenging-the-myth-of-graph-collaborative","title":"Challenging the Myth of Graph Collaborative Filtering: a Reasoned and Reproducibility-driven Analysis","date":"2023-08-01","arxiv_id":"2308.00404","n_code_links":1,"syntology":null},{"paper":null,"title":"GNN4FR: A Lossless GNN-based Federated Recommendation Framework","date":"2023-07-25","arxiv_id":"2308.01197","n_code_links":0,"syntology":null},{"paper":"/paper/how-graph-convolutions-amplify-popularity","title":"How Graph Convolutions Amplify Popularity Bias for Recommendation?","date":"2023-05-24","arxiv_id":"2305.14886","n_code_links":1,"syntology":null},{"paper":null,"title":"Retraining A Graph-based Recommender with Interests Disentanglement","date":"2023-05-05","arxiv_id":"2305.03624","n_code_links":0,"syntology":null},{"paper":"/paper/towards-explainable-collaborative-filtering","title":"Towards Explainable Collaborative Filtering with Taste Clusters Learning","date":"2023-04-27","arxiv_id":"2304.13937","n_code_links":1,"syntology":null},{"paper":"/paper/dual-policy-learning-for-aggregation","title":"Dual Policy Learning for Aggregation Optimization in Graph Neural Network-based Recommender Systems","date":"2023-02-21","arxiv_id":"2302.10567","n_code_links":1,"syntology":null},{"paper":"/paper/bring-your-own-view-graph-neural-networks-for","title":"Bring Your Own View: Graph Neural Networks for Link Prediction with Personalized Subgraph Selection","date":"2022-12-23","arxiv_id":"2212.12488","n_code_links":1,"syntology":null},{"paper":"/paper/mdgcf-multi-dependency-graph-collaborative","title":"MDGCF: Multi-Dependency Graph Collaborative Filtering with Neighborhood- and Homogeneous-level Dependencies","date":"2022-10-17","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"Efficient Graph based Recommender System with Weighted Averaging of Messages","date":"2022-09-30","arxiv_id":"2209.15238","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-missing-data-aleatoric-uncertainty","title":"Rethinking Missing Data: Aleatoric Uncertainty-Aware Recommendation","date":"2022-09-22","arxiv_id":"2209.11679","n_code_links":1,"syntology":null},{"paper":"/paper/svd-gcn-a-simplified-graph-convolution","title":"SVD-GCN: A Simplified Graph Convolution Paradigm for Recommendation","date":"2022-08-26","arxiv_id":"2208.12689","n_code_links":1,"syntology":null},{"paper":"/paper/collaboration-aware-graph-convolutional","title":"Collaboration-Aware Graph Convolutional Network for Recommender Systems","date":"2022-07-03","arxiv_id":"2207.06221","n_code_links":1,"syntology":{"ran":0,"of":1,"unverified":1,"pointer_only":0}},{"paper":"/paper/hypergraph-contrastive-collaborative","title":"Hypergraph Contrastive Collaborative Filtering","date":"2022-04-26","arxiv_id":"2204.12200","n_code_links":1,"syntology":null},{"paper":"/paper/less-is-more-reweighting-important-spectral","title":"Less is More: Reweighting Important Spectral Graph Features for Recommendation","date":"2022-04-24","arxiv_id":"2204.11346","n_code_links":1,"syntology":null},{"paper":"/paper/recommender-may-not-favor-loyal-users","title":"Do Loyal Users Enjoy Better Recommendations? Understanding Recommender Accuracy from a Time Perspective","date":"2022-04-12","arxiv_id":"2204.05927","n_code_links":1,"syntology":null},{"paper":"/paper/ia-gcn-interactive-graph-convolutional","title":"IA-GCN: Interactive Graph Convolutional Network for Recommendation","date":"2022-04-08","arxiv_id":"2204.03827","n_code_links":1,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/recommendation-systems","name":"Recommendation Systems","papers":36},{"task":"/task/collaborative-filtering","name":"Collaborative Filtering","papers":25},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":5},{"task":"/task/graph-neural-network","name":"Graph Neural Network","papers":4},{"task":"/task/representation-learning","name":"Representation Learning","papers":4},{"task":"/task/self-supervised-learning","name":"Self-Supervised Learning","papers":3},{"task":"/task/graph-attention","name":"Graph Attention","papers":2},{"task":"/task/graph-classification","name":"Graph Classification","papers":2},{"task":"/task/graph-representation-learning","name":"Graph Representation Learning","papers":2},{"task":"/task/link-prediction","name":"Link Prediction","papers":2},{"task":"/task/multi-modal-recommendation","name":"Multi-modal Recommendation","papers":2},{"task":"/task/counterfactual-inference","name":"Counterfactual Inference","papers":1},{"task":"/task/counterfactual-reasoning","name":"Counterfactual Reasoning","papers":1},{"task":"/task/decision-making","name":"Decision Making","papers":1},{"task":"/task/denoising","name":"Denoising","papers":1},{"task":"/task/disentanglement","name":"Disentanglement","papers":1},{"task":"/task/entity-embeddings","name":"Entity Embeddings","papers":1},{"task":"/task/graph-learning","name":"Graph Learning","papers":1},{"task":"/task/graph-sampling","name":"Graph Sampling","papers":1},{"task":"/task/incremental-learning","name":"Incremental Learning","papers":1}],"tasks_shown":20,"n_tasks":30,"usage_by_year":[{"year":"2020","papers":3},{"year":"2021","papers":9},{"year":"2022","papers":14},{"year":"2023","papers":10},{"year":"2024","papers":6},{"year":"2025","papers":4}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/lightgcn"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}