Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Transferable Contextual Bandit for Cross-Domain 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 source-domain transfer with exploration (TCB) instead of LinUCB/hLinUCB | contextual bandit · Synthetic bandit | cumulative regret | Helped |
| add exploration to transfer (TCB vs HTL pure exploitation) (ablation) | transfer bandit · Synthetic bandit | cumulative regret | Helped |
| tune alpha manually instead of theory-derived values (ablation) | TCB · Synthetic bandit | cumulative regret | Helped |
| raise exploration alpha above 0.2 (ablation) | TCB, LinUCB, hLinUCB · Synthetic bandit | cumulative regret | Hurt |
| use alpha = 0 (pure exploitation) (ablation) | bandit policies · Synthetic bandit | cumulative regret | Hurt |
| reduce source observations to 1,000 (ablation) | TCB · Synthetic bandit | cumulative regret | Hurt |
| increase correspondence density from very sparse to moderate (ablation) | TCB · Synthetic bandit | cumulative regret | Mixed |
| add transfer from app domain (TCB) vs LinUCB/hLinUCB | contextual bandit · Cheetah data (heterogeneous) | normalized cumulative reward | Helped |
| add exploration to transfer (TCB vs HTL) (ablation) | transfer bandit · Cheetah data | normalized cumulative reward | Mixed |
| use cross-domain transfer (TCB) instead of collaborative filtering hLinUCB/FactorUCB | contextual bandit · Delicious data (homogeneous) | normalized cumulative reward | Helped |
Closest papers by meaning
- Contextual-Bandit Based Personalized Recommendation with Time-Varying User Interests (AAAI 2020 · similarity 0.88)
- Towards Domain Adaptive Neural Contextual Bandits (ICLR 2025 · similarity 0.87)
- Simple Projection-Free Algorithm for Contextual Recommendation with Logarithmic Regret and Robustness (NeurIPS 2026 · similarity 0.86)
- Neural Combinatorial Clustered Bandits for Recommendation Systems (AAAI 2025 · similarity 0.85)
- Efficient Contextual Bandits with Uninformed Feedback Graphs (ICML 2024 · similarity 0.85)
- High Probability Bound for Cross-Learning Contextual Bandits with Unknown Context Distributions (ICML 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.