Research map / Label-efficient and robust learning / Domain adaptation and generalization
Multi-Domain Active Learning for Recommendation
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 |
|---|---|---|---|
| add domain-independent (variance) term to domain-specific expected-entropy selection (ablation) | multi-domain active learning on RMGM · ML+EM+NF | overall RMSE: 1.0719 -> 1.0665 | Helped |
| add domain-specific entropy term to domain-independent variance selection (ablation) | multi-domain active learning on RMGM · ML+EM+NF | overall RMSE: 1.0779 -> 1.0665 | Helped |
| select pairs globally across domains instead of per domain (specific-only criterion) | active learning strategy · ML+EM+NF | overall RMSE: 1.0826 -> 1.0719 | Helped |
| global random selection instead of per-domain random | random active learning · ML+EM+NF | overall RMSE: 1.0798 -> 1.0815 | Hurt |
| MultiAL vs best baseline on label efficiency for 0.1 RMSE reduction (ML+EM+NF) | MultiAL · ML+EM+NF | ratings needed: 10800 -> 9600 | Helped |
| MultiAL vs best baseline on label efficiency for 0.15 RMSE reduction (ML+EM+NF) | MultiAL · ML+EM+NF | ratings needed: 21600 -> 20400 | Helped |
| vary weight mu of domain-independent term from 0.001 to 1000 (omega=1) (ablation) | MultiAL · five tasks | RMSE after 10 iterations: mu=1 best | Helped |
| vary labeled pairs per iteration S from 50 to 2000 (ablation) | MultiAL · five tasks | RMSE | No clear effect |
Closest papers by meaning
- One for Dozens: Adaptive REcommendation for All Domains with Counterfactual Augmentation (AAAI 2025 · similarity 0.87)
- Active Large Language Model-Based Knowledge Distillation for Session-Based Recommendation (AAAI 2025 · similarity 0.86)
- Domain-Level Disentanglement Framework Based on Information Enhancement for Cross-Domain Cold-Start Recommendation (AAAI 2025 · similarity 0.85)
- Composite Active Learning: Towards Multi-Domain Active Learning with Theoretical Guarantees (AAAI 2024 · similarity 0.84)
- Federated Graph Learning for Cross-Domain Recommendation (NeurIPS 2024 · similarity 0.84)
- Towards Unbiased Information Extraction and Adaptation in Cross-Domain Recommendation (AAAI 2025 · 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.