Recommendation Systems
LightGCN
Introduced by He et al. in LightGCN: Simplifying and Powering Graph Convolution Network for RecommendationLightGCN 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.
Source: LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Recommendation Systems | 28 | 40.58% |
| Collaborative Filtering | 19 | 27.54% |
| Self-Supervised Learning | 3 | 4.35% |
| Graph Attention | 2 | 2.90% |
| Graph Classification | 2 | 2.90% |
| Graph Representation Learning | 2 | 2.90% |
| Link Prediction | 2 | 2.90% |
| Graph Sampling | 1 | 1.45% |
| Disentanglement | 1 | 1.45% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
