Research map / Learning theory and algorithms / Prediction and decision losses
Extreme Learning to Rank via Low Rank Assumption
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 factorized low-rank ranking (rank 20) instead of one joint RankSVM | Factorization RankSVM · Synthetic | test accuracy: 0.508 -> 0.964 | Helped |
| use factorized low-rank ranking (rank 20) instead of separate per-user RankSVMs | Factorization RankSVM · Synthetic | test accuracy: 0.808 -> 0.964 | Helped |
| use factorized ranking instead of multi-task RankSVM Var | Factorization RankSVM · Synthetic | test accuracy: 0.719 -> 0.964 | Helped |
| choose rank 10 (below true rank 20) (ablation) | Factorization RankSVM · Synthetic | test accuracy: 0.964 -> 0.820 | Hurt |
| choose rank 30 (above true rank 20) (ablation) | Factorization RankSVM · Synthetic | test accuracy: 0.964 -> 0.943 | Hurt |
| factorized model versus separate RankSVMs on training time | Factorization RankSVM · Yahoo! Movies | time per epoch (s): 130 -> 2.85 | Helped |
| factorized model versus multi-task RankSVM Var on speed | Factorization RankSVM · Yahoo! Movies | time per epoch (s): 309 -> 2.85 | Helped |
| increase rank from 100 to 200 (ablation) | Factorization RankSVM · Yahoo! Movies | test accuracy: 0.804 -> 0.775 | Hurt |
| rank 100 versus rank 30 (ablation) | Factorization RankSVM · Yahoo! Movies | test accuracy: 0.770 -> 0.804 | Helped |
| factorized model versus inductive matrix completion (rating input) | Factorization RankSVM · Yahoo! Movies | test accuracy: 0.802 -> 0.804 | No clear effect |
| factorized model versus joint RankSVM | Factorization RankSVM · HetRec2011-MovieLens-2K | test accuracy: 0.619 -> 0.651 | Helped |
| increase rank from 150 to 250 (ablation) | Factorization RankSVM · HetRec2011-MovieLens-2K | test accuracy: 0.651 -> 0.650 | No clear effect |
Closest papers by meaning
- A Batch Learning Framework for Scalable Personalized Ranking (AAAI 2018 · similarity 0.87)
- TopRank: A practical algorithm for online stochastic ranking (NeurIPS 2018 · similarity 0.86)
- PiRank: Scalable Learning To Rank via Differentiable Sorting (NeurIPS 2021 · similarity 0.86)
- Which Tricks are Important for Learning to Rank? (ICML 2023 · similarity 0.86)
- From Pairwise to Ranking: Climbing the Ladder to Ideal Collaborative Filtering with Pseudo-Ranking (AAAI 2025 · similarity 0.85)
- Adaptively Learning to Select-Rank in Online Platforms (ICML 2024 · similarity 0.83)
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.