Research map / Label-efficient and robust learning / Knowledge distillation
Explicit Intent-Enhanced Knowledge Distillation for Trip Recommendation
Shuliang Wang, Xiaoting Leng, Sijie Ruan, Dingqi Yang, Yicheng Tang, Qianyu Yang, Qianxiong Xu, Jiabao Zhu, Hanning Yuan
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 knowledge distillation from trajectory encoder (ablation) | EKD-Trip · Toronto, Tokyo | F1 and pairs-F1 | Improved |
| add travel mode prediction head (ablation) | EKD-Trip · Toronto, Tokyo | F1 and pairs-F1 | Improved |
| add context-aware mechanism in trip generator (ablation) | EKD-Trip · Toronto, Tokyo | F1 and pairs-F1 | Improved |
| use bidirectional Mamba instead of Transformer (ablation) | EKD-Trip · Toronto, Tokyo | F1 | Improved |
| add dedicated query encoder (ablation) | EKD-Trip · Toronto, Tokyo | F1 and pairs-F1 | Improved |
| add travel mode prediction to Bert-Trip (ablation) | Bert-Trip · Toronto, Tokyo | F1 and pairs-F1 | Improved |
| vary lambda between KD and mode prediction from 0.3 to 0.7 (ablation) | EKD-Trip · Toronto, Tokyo | F1 and pairs-F1: peak at lambda = 0.6 | Mixed |
| EKD-Trip vs best baseline pairs-F1 | EKD-Trip · four cities | pairs-F1: 13.70% average improvement in pairs-F1 | Improved |
Closest papers by meaning
- Faithful Trip Recommender Using Diffusion Guidance (Student Abstract) (AAAI 2024 · similarity 0.87)
- SPOT-Trip: Dual-Preference Driven Out-of-Town Trip Recommendation (NeurIPS 2025 · similarity 0.86)
- Active Large Language Model-Based Knowledge Distillation for Session-Based Recommendation (AAAI 2025 · similarity 0.85)
- Spatial-Temporal Knowledge Distillation for Takeaway Recommendation (AAAI 2025 · similarity 0.85)
- Intent Oriented Contrastive Learning for Sequential Recommendation (AAAI 2025 · similarity 0.84)
- TRACE: Tourism Recommendation with Accountable Citation Evidence (NeurIPS 2026 · similarity 0.83)
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.
