Research map / Learning theory and algorithms / Clustering
GLOMA: Embedding Global Information in Local Matrix Approximation Models for Collaborative Filtering
Chao Chen, Dongsheng Li, Qin Lv, Junchi Yan, Li Shang, Stephen Chu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| embed a global MA model into local models (GLOMA) instead of ensembles of local models | clustering-based MA · MovieLens 10M | RMSE: 0.7734 -> 0.7672 vs WEMAREC | Improved |
| GLOMA vs strongest baseline MPMA | collaborative filtering · Netflix | RMSE: 0.8083 -> 0.8011 | Improved |
| replace K-means++ with data-projected clustering (DSDP) (ablation) | GLOMA clustering · MovieLens 10M | clustering time (s): 7554.522 -> 4.242 | Improved |
| replace K-means++ with DSDP clustering (ablation) | GLOMA · MovieLens 10M | RMSE | Improved |
| replace random partition with meaningful clustering (KMPP or DSDP) (ablation) | GLOMA · MovieLens 10M | RMSE | Improved |
| enable both embedded user and item features (pi1, pi2 > 0) instead of only one or none (ablation) | GLOMA · MovieLens 1M, rank 10 | RMSE | Improved |
| train embedded model on more training data (ablation) | GLOMA · MovieLens 10M | RMSE | Improved |
| use a randomly established embedded model (0% data) (ablation) | GLOMA · MovieLens 10M | RMSE: RMSE less than 0.7800 | Improved |
| increase number of clusters (ablation) | GLOMA · MovieLens 10M, rank 20 | RMSE | Hurt |
| increase rank from 20 to 100 (ablation) | GLOMA vs RSVD · MovieLens 10M | RMSE | Mixed |
Closest papers by meaning
- Mitigating the Popularity Bias of Graph Collaborative Filtering: A Dimensional Collapse Perspective (NeurIPS 2023 · similarity 0.85)
- Towards Open-World Recommendation: An Inductive Model-based Collaborative Filtering Approach (ICML 2021 · similarity 0.85)
- Graph Heterogeneous Multi-Relational Recommendation (AAAI 2021 · similarity 0.85)
- Recommendations with Sparse Comparison Data: Provably Fast Convergence for Nonconvex Matrix Factorization (ICML 2025 · similarity 0.84)
- Learning-Efficient Yet Generalizable Collaborative Filtering for Item Recommendation (ICML 2024 · similarity 0.84)
- FACE: A General Framework for Mapping Collaborative Filtering Embeddings into LLM Tokens (NeurIPS 2025 · similarity 0.84)
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.
