Research map / Probabilistic and scientific modeling / Molecules and proteins
SetRank: A Setwise Bayesian Approach for Collaborative Ranking from Implicit Feedback
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 setwise Bayesian ranking with a neural-network score model instead of Multi-VAE | Implicit-feedback recommendation · MovieLens | P@5: 0.6806 ± 0.0012 -> 0.6956 ± 0.0030 | Helped |
| Use setwise Bayesian ranking with a neural-network score model instead of MF-SetRank | Implicit-feedback recommendation · Kindle | P@5: 0.1773 ± 0.0027 -> 0.1837 ± 0.0020 | Helped |
| Use setwise Bayesian ranking with a neural-network score model instead of Multi-VAE | Implicit-feedback recommendation · Yahoo | P@5: 0.2300 ± 0.0018 -> 0.2372 ± 0.0011 | Helped |
| Use setwise Bayesian ranking with a neural-network score model instead of Deep-BPR | Implicit-feedback recommendation · CiteULike | P@5: 0.2086 ± 0.0009 -> 0.2233 ± 0.0026 | Helped |
| Increase the negative-sampling ratio beyond τ=3 (ablation) | SetRank · MovieLens, Kindle, Yahoo, and CiteULike | P@5 | No clear effect |
| Use a larger latent-factor rank instead of r=50 (ablation) | MF-SetRank · MovieLens, Kindle, Yahoo, and CiteULike | P@5 | Helped |
| Use rank r=100 for the neural implementation (ablation) | Deep-SetRank · MovieLens, Kindle, Yahoo, and CiteULike | P@5 | No clear effect |
Closest papers by meaning
- SQL-Rank: A Listwise Approach to Collaborative Ranking (ICML 2018 · similarity 0.91)
- From Pairwise to Ranking: Climbing the Ladder to Ideal Collaborative Filtering with Pseudo-Ranking (AAAI 2025 · similarity 0.88)
- WalkRanker: A Unified Pairwise Ranking Model With Multiple Relations for Item Recommendation (AAAI 2018 · similarity 0.88)
- GoalRank: Group-Relative Optimization for a Large Ranking Model (ICLR 2026 · similarity 0.87)
- Preference Diffusion for Recommendation (ICLR 2025 · similarity 0.86)
- PSL: Rethinking and Improving Softmax Loss from Pairwise Perspective for Recommendation (NeurIPS 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.