Research map / Learning theory and algorithms / Matrix and tensor methods
SQL-Rank: A Listwise Approach to Collaborative Ranking
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 stochastic queuing to resample tie orderings during training rather than fixing one ordering (ablation) | SQL-Rank · Movielens1m | P@1: 0.62763 -> 0.73685 | Helped |
| Use stochastic queuing to resample tie orderings during training rather than fixing one ordering (ablation) | SQL-Rank · Movielens1m | P@5: 0.58420 -> 0.67167 | Helped |
| Use stochastic queuing to resample tie orderings during training rather than fixing one ordering (ablation) | SQL-Rank · Movielens1m | P@10: 0.55036 -> 0.61833 | Helped |
| Increase listwise likelihood depth from k=5 to k=10 (ablation) | SQL-Rank · Movielens1m | NDCG@10: 0.64807 -> 0.67746 | Helped |
| Increase listwise likelihood depth from k=10 to k=25 (ablation) | SQL-Rank · Movielens1m | NDCG@10: 0.67746 -> 0.74589 | Helped |
| Use the full observed list instead of k=25 (ablation) | SQL-Rank · Movielens1m | NDCG@10: 0.74589 -> 0.75076 | Helped |
| Use SQL-Rank instead of List-MF's top-1 cross-entropy listwise loss | collaborative ranking · Movielens1m explicit feedback | P@1: 0.45226 -> 0.50736 | Helped |
| Use SQL-Rank instead of Primal-CR++ | collaborative ranking · Movielens1m explicit feedback | NDCG@10: 0.76826 -> 0.75076 | Hurt |
Closest papers by meaning
- SetRank: A Setwise Bayesian Approach for Collaborative Ranking from Implicit Feedback (AAAI 2020 · similarity 0.91)
- From Pairwise to Ranking: Climbing the Ladder to Ideal Collaborative Filtering with Pseudo-Ranking (AAAI 2025 · similarity 0.90)
- WalkRanker: A Unified Pairwise Ranking Model With Multiple Relations for Item Recommendation (AAAI 2018 · similarity 0.89)
- ScoreNet: Consistency-driven Framework with Multi-side Information Fusion for Session-based Recommendation (AAAI 2025 · similarity 0.84)
- Preference Diffusion for Recommendation (ICLR 2025 · similarity 0.84)
- Learning-Efficient Yet Generalizable Collaborative Filtering for Item Recommendation (ICML 2024 · 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.