Methods › Graphs › Graph Models › LightGCN
LightGCN
Introduced by Xiangnan He et al. in LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
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 archive 2025-07-28
30 shown of 46, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Improvement Graph Convolution Collaborative Filtering with Weighted addition input 27 Mar 2025 · 1 repository · arXiv:2503.21468
-
Rolling Forward: Enhancing LightGCN with Causal Graph Convolution for Credit Bond Recommendation 18 Mar 2025 · 0 repositories · arXiv:2503.14213
-
Hypergraph Diffusion for High-Order Recommender Systems 28 Jan 2025 · 0 repositories · arXiv:2501.16722
-
Graph Neural Controlled Differential Equations For Collaborative Filtering 23 Jan 2025 · 1 repository · arXiv:2501.13908
-
Position-aware Graph Transformer for Recommendation 25 Dec 2024 · 0 repositories · arXiv:2412.18731
-
A Novel Evaluation Perspective on GNNs-based Recommender Systems through the Topology of the User-Item Graph 21 Aug 2024 · 1 repository · arXiv:2408.11762
-
Bundle Recommendation with Item-level Causation-enhanced Multi-view Learning 13 Aug 2024 · 1 repository · arXiv:2408.08906
-
SimCE: Simplifying Cross-Entropy Loss for Collaborative Filtering 23 Jun 2024 · 1 repository · arXiv:2406.16170
-
Balancing Embedding Spectrum for Recommendation 17 Jun 2024 · 1 repository · arXiv:2406.12032
-
Wasserstein Dependent Graph Attention Network for Collaborative Filtering with Uncertainty 9 Apr 2024 · 0 repositories · arXiv:2404.05962
-
LightGCN: Evaluated and Enhanced 17 Dec 2023 · 1 repository · arXiv:2312.16183
-
VM-Rec: A Variational Mapping Approach for Cold-start User Recommendation 2 Nov 2023 · 1 repository · arXiv:2311.01304
-
A Topology-aware Analysis of Graph Collaborative Filtering 21 Aug 2023 · 1 repository · arXiv:2308.10778
-
Toward a Better Understanding of Loss Functions for Collaborative Filtering 11 Aug 2023 · 1 repository · arXiv:2308.06091
-
Challenging the Myth of Graph Collaborative Filtering: a Reasoned and Reproducibility-driven Analysis 1 Aug 2023 · 1 repository · arXiv:2308.00404
-
GNN4FR: A Lossless GNN-based Federated Recommendation Framework 25 Jul 2023 · 0 repositories · arXiv:2308.01197
-
How Graph Convolutions Amplify Popularity Bias for Recommendation? 24 May 2023 · 1 repository · arXiv:2305.14886
-
Retraining A Graph-based Recommender with Interests Disentanglement 5 May 2023 · 0 repositories · arXiv:2305.03624
-
Towards Explainable Collaborative Filtering with Taste Clusters Learning 27 Apr 2023 · 1 repository · arXiv:2304.13937
-
Dual Policy Learning for Aggregation Optimization in Graph Neural Network-based Recommender Systems 21 Feb 2023 · 1 repository · arXiv:2302.10567
-
Bring Your Own View: Graph Neural Networks for Link Prediction with Personalized Subgraph Selection 23 Dec 2022 · 1 repository · arXiv:2212.12488
-
MDGCF: Multi-Dependency Graph Collaborative Filtering with Neighborhood- and Homogeneous-level Dependencies 17 Oct 2022 · 1 repository
-
Efficient Graph based Recommender System with Weighted Averaging of Messages 30 Sep 2022 · 0 repositories · arXiv:2209.15238
-
Rethinking Missing Data: Aleatoric Uncertainty-Aware Recommendation 22 Sep 2022 · 1 repository · arXiv:2209.11679
-
SVD-GCN: A Simplified Graph Convolution Paradigm for Recommendation 26 Aug 2022 · 1 repository · arXiv:2208.12689
-
Collaboration-Aware Graph Convolutional Network for Recommender Systems 3 Jul 2022 · 1 repository · arXiv:2207.06221Syntology ran 0 of 1 samples · 1 unverified
-
Hypergraph Contrastive Collaborative Filtering 26 Apr 2022 · 1 repository · arXiv:2204.12200
-
Less is More: Reweighting Important Spectral Graph Features for Recommendation 24 Apr 2022 · 1 repository · arXiv:2204.11346
-
Do Loyal Users Enjoy Better Recommendations? Understanding Recommender Accuracy from a Time Perspective 12 Apr 2022 · 1 repository · arXiv:2204.05927
-
IA-GCN: Interactive Graph Convolutional Network for Recommendation 8 Apr 2022 · 1 repository · arXiv:2204.03827
Tasks archive 2025-07-28
20 shown of 30 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections