Research map / Learning theory and algorithms / Matrix and tensor methods
Multivariate Spearman's $\rho$ for Aggregating Ranks Using Copulas
Justin Bedő, Cheng Soon Ong
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 |
|---|---|---|---|
| add learned expert weights and imputation (RAGS-⊤) over geometric mean (ablation) | GeoMean · MQ2007-agg | NDCG@1: 0.42264 -> 0.45986 | Improved |
| add learned expert weights and imputation (RAGS-⊤) over geometric mean (ablation) | GeoMean · MQ2008-agg | NDCG@5: 0.47938 -> 0.50696 | Improved |
| use RAGS-⊤ instead of the bottom-k imputation RAGS-⊥ | RAGS · MQ2007-agg | NDCG@10: 0.38458 -> 0.4858 | Improved |
| use RAGS-⊤ instead of best prior St.Agg | St.Agg · MQ2007-agg | NDCG@10: 0.4404 -> 0.4858 | Improved |
| use RAGS-⊤ instead of θ-MPM | θ-MPM · MQ2008-agg | NDCG@5: 0.4399 -> 0.50696 | Improved |
| use RAGS-⊤ instead of CPS-S (pairwise Spearman) | CPS-S · MQ2007-agg | NDCG@2: 0.332 -> 0.46078 | Improved |
| use geometric mean instead of Borda count | Borda · MQ2007-agglist | Spearman's rho: 0.2217 -> 0.2457 | Improved |
| use geometric mean instead of Borda count | Borda · MQ2008-agglist | Kendall's tau: 0.5869 -> 0.6578 | Improved |
| optimise Spearman's rho (RAGS-⊤) rather than a tau-oriented aggregate | GeoMean · MQ2008-agglist | Kendall's tau: 0.6578 -> 0.6931 | Mixed |
| optimise Spearman's rho (RAGS-⊤) vs GeoMean | GeoMean · MQ2007-agglist | Spearman's rho: 0.2457 -> 0.4394 | Improved |
| use relaxed optimal imputation instead of non-informative extension | non-informative extension · University rankings | multivariate Spearman's rho: 0.632 -> 0.683 | Improved |
Closest papers by meaning
- Statistical Inference for Incomplete Ranking Data: The Case of Rank-Dependent Coarsening (ICML 2017 · similarity 0.88)
- Data-driven Rank Breaking for Efficient Rank Aggregation (ICML 2016 · similarity 0.87)
- Rank Aggregation via Heterogeneous Thurstone Preference Models (AAAI 2020 · similarity 0.87)
- Improved Differentially Private Algorithms for Rank Aggregation (AAAI 2026 · similarity 0.85)
- Stability and Multigroup Fairness in Ranking with Uncertain Predictions (ICML 2024 · similarity 0.84)
- Beyond Kemeny Medians: Consensus Ranking Distributions. Definition, Properties and Statistical Learning (NeurIPS 2026 · 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.
