Analyzing and Mitigating Repetitions in Trip Recommendation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908468575731712 |
|---|---|
| author | Shu, Wenzheng Xu, Kangqi Tai, Wenxin Zhong, Ting Wang, Yong Zhou, Fan |
| author_facet | Shu, Wenzheng Xu, Kangqi Tai, Wenxin Zhong, Ting Wang, Yong Zhou, Fan |
| contents | Trip recommendation has emerged as a highly sought-after service over the past decade. Although current studies significantly understand human intention consistency, they struggle with undesired repetitive outcomes that need resolution. We make two pivotal discoveries using statistical analyses and experimental designs: (1) The occurrence of repetitions is intricately linked to the models and decoding strategies. (2) During training and decoding, adding perturbations to logits can reduce repetition. Motivated by these observations, we introduce AR-Trip (Anti Repetition for Trip Recommendation), which incorporates a cycle-aware predictor comprising three mechanisms to avoid duplicate Points-of-Interest (POIs) and demonstrates their effectiveness in alleviating repetition. Experiments on four public datasets illustrate that AR-Trip successfully mitigates repetition issues while enhancing precision. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_19798 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Analyzing and Mitigating Repetitions in Trip Recommendation Shu, Wenzheng Xu, Kangqi Tai, Wenxin Zhong, Ting Wang, Yong Zhou, Fan Information Retrieval Machine Learning Trip recommendation has emerged as a highly sought-after service over the past decade. Although current studies significantly understand human intention consistency, they struggle with undesired repetitive outcomes that need resolution. We make two pivotal discoveries using statistical analyses and experimental designs: (1) The occurrence of repetitions is intricately linked to the models and decoding strategies. (2) During training and decoding, adding perturbations to logits can reduce repetition. Motivated by these observations, we introduce AR-Trip (Anti Repetition for Trip Recommendation), which incorporates a cycle-aware predictor comprising three mechanisms to avoid duplicate Points-of-Interest (POIs) and demonstrates their effectiveness in alleviating repetition. Experiments on four public datasets illustrate that AR-Trip successfully mitigates repetition issues while enhancing precision. |
| title | Analyzing and Mitigating Repetitions in Trip Recommendation |
| topic | Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2507.19798 |