Research map / Graph learning / Graph algorithms and clustering
Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use RGCNN instead of GRALS with users and items graphs | Synthetic matrix completion · Synthetic, users+items graphs | RMSE: 0.0114 -> 0.0053 | Helped |
| Use sRGCNN instead of GRALS with users and items graphs | Synthetic matrix completion · Synthetic, users+items graphs | RMSE: 0.0114 -> 0.0106 | Helped |
| Use sRGCNN instead of GRALS with only the users graph | Synthetic matrix completion · Synthetic, users graph only | RMSE: 0.0452 -> 0.0362 | Helped |
| Use sRGCNN instead of GRALS | MovieLens matrix completion · MovieLens | RMSE: 0.945 -> 0.929 | Helped |
| Use sRGCNN instead of GRALS with users and items graphs | Flixster matrix completion · Flixster, users+items graphs | RMSE: 1.3126 -> 1.1788 | Helped |
| Use sRGCNN instead of GRALS with only the users graph | Flixster matrix completion · Flixster, users graph only | RMSE: 1.2447 -> 0.9258 | Helped |
| Use sRGCNN instead of GRALS with the user graph | Douban matrix completion · Douban | RMSE: 0.8326 -> 0.8012 | Helped |
| Use sRGCNN instead of GRALS with the item graph | YahooMusic matrix completion · YahooMusic | RMSE: 38.0423 -> 22.4149 | Helped |
Closest papers by meaning
- Inductive Matrix Completion Based on Graph Neural Networks (ICLR 2020 · similarity 0.90)
- Feature-Structure Adaptive Completion Graph Neural Network for Cold-start Recommendation (AAAI 2025 · similarity 0.86)
- Hgformer: Hyperbolic Graph Transformer for Collaborative Filtering (ICML 2025 · similarity 0.86)
- Beyond Graph Convolution: Multimodal Recommendation with Topology-aware MLPs (AAAI 2025 · similarity 0.86)
- ContextGNN: Beyond Two-Tower Recommendation Systems (ICLR 2025 · similarity 0.85)
- Spectral-Based Graph Neural Networks for Complementary Item Recommendation (AAAI 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.