Research map / Label-efficient and robust learning / Recognition and long-tail
From Common to Special: When Multi-Attribute Learning Meets Personalized Opinions
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 common-to-special model with global, attribute-specific, and user-specific factors instead of the strongest listed baseline | User-specific binary attribute learning · Shoes binary attributes, 40% training | accuracy: 0.6771 -> 0.6894 | Helped |
| Use the common-to-special model with global, attribute-specific, and user-specific factors instead of rMTFL-U | User-specific binary attribute learning · Shoes binary attributes, 80% training | accuracy: 0.7056 -> 0.7121 | Helped |
| Use the common-to-special model with global, attribute-specific, and user-specific factors instead of rMTFL-U | User-specific relative attribute learning · Shoes relative attributes, 40% training | accuracy: 0.4838 -> 0.5119 | Helped |
| Use the common-to-special model with global, attribute-specific, and user-specific factors instead of rMTFL-U | User-specific relative attribute learning · Shoes relative attributes, 80% training | accuracy: 0.5433 -> 0.5546 | Helped |
| Use the common-to-special model instead of Lasso | Simulated attribute regression · Simulated dataset, 40% training | NMSE: 3.28E-05 -> 2.95E-05 | Helped |
| Use the common-to-special model instead of Lasso | Simulated attribute regression · Simulated dataset, 80% training | NMSE: 2.35E-05 -> 2.18E-05 | Helped |
| Add Nesterov acceleration to the proximal algorithm (ablation) | Proposed model optimization · Simulated dataset, 40% and 80% training | convergence speed | Helped |
Closest papers by meaning
- Learning Personalized Attribute Preference via Multi-Task AUC Optimization (AAAI 2019 · similarity 0.86)
- Learning Attributes Equals Multi-Source Domain Generalization (CVPR 2016 · similarity 0.86)
- Navigating Real-World Partial Label Learning: Unveiling Fine-Grained Images with Attributes (AAAI 2024 · similarity 0.84)
- Unbiased Multi-Label Learning from Crowdsourced Annotations (ICML 2024 · similarity 0.84)
- Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and Beyond (ICLR 2024 · similarity 0.83)
- Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language Recognition (ICLR 2025 · similarity 0.82)
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.