Research map / Learning theory and algorithms / Prediction and decision losses
Learning Personalized Attribute Preference via Multi-Task AUC Optimization
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 the proposed multi-level personalized AUC model instead of the strongest baseline | Personalized attribute learning · Simulation dataset | AUC: 83.57 -> 99.65 | Helped |
| Use the proposed multi-level personalized AUC model instead of the strongest baseline | Personalized attribute learning · Shoes attributes | AUC: 84.24 -> 92.95; 88.68 -> 90.92; 69.66 -> 73.24; 89.19 -> 92.65; 80.93 -> 87.95; 72.99 -> 81.07; 77.62 -> 86.22 | Helped |
| Use the proposed multi-level personalized AUC model instead of the strongest baseline | Personalized attribute learning · SUN attributes | AUC: 72.95 -> 79.31; 69.25 -> 78.19; 76.93 -> 86.50; 74.39 -> 81.88; 72.82 -> 78.98 | Helped |
| Replace original pairwise AUC evaluation with the efficient evaluation scheme | Proposed model · Simulation dataset, 20% training ratio | running time (seconds): 18.57 -> 3.06 | Helped |
| Replace original pairwise AUC evaluation with the efficient evaluation scheme | Proposed model · Simulation dataset, 40% training ratio | running time (seconds): 74.22 -> 5.50 | Helped |
| Replace original pairwise AUC evaluation with the efficient evaluation scheme | Proposed model · Simulation dataset, 60% training ratio | running time (seconds): 151.86 -> 8.65 | Helped |
| Replace original pairwise AUC evaluation with the efficient evaluation scheme | Proposed model · Simulation dataset, 80% training ratio | running time (seconds): 268.55 -> 12.46 | Helped |
| Replace original pairwise AUC evaluation with the efficient evaluation scheme | Proposed model · Simulation dataset, 100% training ratio | running time (seconds): nan -> 15.82 | Helped |
Closest papers by meaning
- Active preference learning for ordering items in- and out-of-sample (NeurIPS 2024 · similarity 0.82)
- AUC Optimization from Multiple Unlabeled Datasets (AAAI 2024 · similarity 0.81)
- Personalized Clustering via Targeted Representation Learning (AAAI 2025 · similarity 0.81)
- Regularized Conditional Diffusion Model for Multi-Task Preference Alignment (NeurIPS 2024 · similarity 0.81)
- Class-Attribute Priors: Adapting Optimization to Heterogeneity and Fairness Objective (AAAI 2024 · similarity 0.81)
- Preference Diffusion for Recommendation (ICLR 2025 · similarity 0.80)
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.