Research map / Architectures and efficiency / Pruning and efficient tuning
Breaking Down Market Barriers: Distilled Prompt-Tuning Approach for Cross-Market Recommendation
Leqi Zhang, Wayne Lu, Haiyang Zhang, Elliott Wen, Zhixuan Liang, Jia Wang
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 multi-market pre-training (ablation) | DCMPT · XMarket de | NDCG@10: 0.139 -> 0.390 | Improved |
| add multi-market pre-training (ablation) | DCMPT · XMarket ca | NDCG@10: 0.028 -> 0.264 | Improved |
| add prompt tuning (ablation) | DCMPT · XMarket jp | NDCG@10: 0.214 -> 0.566 | Improved |
| add distillation losses (ablation) | DCMPT · XMarket mx | NDCG@10: 0.310 -> 0.419 | Improved |
| add WRD (ablation) | DCMPT · XMarket uk | NDCG@10: 0.430 -> 0.502 | Improved |
| add AMRDD (ablation) | DCMPT · XMarket ca | NDCG@10: 0.218 -> 0.264 | Improved |
| prompt tuning with frozen backbone vs fine-tuning based CMR | DCMPT · XMarket uk | Recall@10: 0.6238 -> 0.6739 | Improved |
| prompt tuning with frozen backbone vs fine-tuning based CMR | DCMPT · XMarket uk | training time: 37 min -> 9 min | Improved |
| proposed DCMPT vs best baseline | DCMPT · XMarket in | NDCG@10: 0.5713 -> 0.5850 | Improved |
| number of prompts and alpha weight (ablation) | DCMPT · XMarket mx/ca | NDCG@10 | Mixed |
Closest papers by meaning
- Cross-Task Knowledge Distillation in Multi-Task Recommendation (AAAI 2022 · similarity 0.84)
- Learning Accurate and Bidirectional Transformation via Dynamic Embedding Transportation for Cross-Domain Recommendation (AAAI 2024 · similarity 0.83)
- Addressing Cold-Start Problem in Click-Through Rate Prediction via Supervised Diffusion Modeling (AAAI 2025 · similarity 0.83)
- GeoReward: Mitigating Contextual Variable Overestimation in Vision-Language Models for Cross-Market Preference Prediction (ICML 2026 · similarity 0.83)
- Transfer Faster, Price Smarter: Minimax Dynamic Pricing under Cross-Market Preference Shift (NeurIPS 2025 · similarity 0.82)
- Re2LLM: Reflective Reinforcement Large Language Model for Session-based Recommendation (AAAI 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.
