Research map / Probabilistic and scientific modeling / Molecules and proteins
Coupled Poisson Factorization Integrated With User/Item Metadata for Modeling Popular and Sparse Ratings in Scalable Recommendation
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 |
|---|---|---|---|
| model coupling between users/items to capture rating popularity and sparsity (CPF) instead of plain PF weighting | Hierarchical Poisson Factorization (HPF) · Movielens100K/1M/10M, Book-Crossing | mean precision and recall at top-20: up to 11% improvement of mean precision on Book-Crossing | Helped |
| integrate user/item metadata (mCPF versus CPF) (ablation) | CPF · Movielens and Book-Crossing | precision and recall at top-20 | Helped |
| metadata integration when only item genre metadata is available | mCPF · Movielens10M | precision and recall at top-20 | No clear effect |
| CPF/mCPF versus HPF on recommending popular low-rated items | HPF · Movielens1M and Book-Crossing, top-100 | popularity level (false recommendations of low-rated items) | Helped |
| CPF versus HPF on recommending sparse high-rated items | HPF · Movielens1M and Book-Crossing, top-100 | sparsity level | Helped |
| CuPF versus HPF in a single-user case study | HPF · Movielens100K user 184 top-10 | correct hits | Helped |
Closest papers by meaning
- Gamma-Poisson Dynamic Matrix Factorization Embedded with Metadata Influence (NeurIPS 2018 · similarity 0.92)
- Hierarchical Compound Poisson Factorization (ICML 2016 · similarity 0.91)
- Ordinal Non-negative Matrix Factorization for Recommendation (ICML 2020 · similarity 0.88)
- Recommendations with Sparse Comparison Data: Provably Fast Convergence for Nonconvex Matrix Factorization (ICML 2025 · similarity 0.86)
- Preference Diffusion for Recommendation (ICLR 2025 · similarity 0.84)
- Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for Recommendation (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.