When and What to Recommend: Joint Modeling of Timing and Content for Active Sequential 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_ | 1866915634834571264 |
|---|---|
| author | Chai, Jin Ma, Xiaoxiao Yang, Jian Wu, Jia |
| author_facet | Chai, Jin Ma, Xiaoxiao Yang, Jian Wu, Jia |
| contents | Sequential recommendation models user preferences to predict the next target item. Most existing work is passive, where the system responds only when users open the application, missing chances after closure. We investigate active recommendation, which predicts the next interaction time and actively delivers items. Two challenges: accurately estimating the Time of Interest (ToI) and generating Item of Interest (IoI) conditioned on the predicted ToI. We propose PASRec, a diffusion-based framework that aligns ToI and IoI via a joint objective. Experiments on five benchmarks show superiority over eight state-of-the-art baselines under leave-one-out and temporal splits. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_18717 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | When and What to Recommend: Joint Modeling of Timing and Content for Active Sequential Recommendation Chai, Jin Ma, Xiaoxiao Yang, Jian Wu, Jia Information Retrieval Machine Learning Sequential recommendation models user preferences to predict the next target item. Most existing work is passive, where the system responds only when users open the application, missing chances after closure. We investigate active recommendation, which predicts the next interaction time and actively delivers items. Two challenges: accurately estimating the Time of Interest (ToI) and generating Item of Interest (IoI) conditioned on the predicted ToI. We propose PASRec, a diffusion-based framework that aligns ToI and IoI via a joint objective. Experiments on five benchmarks show superiority over eight state-of-the-art baselines under leave-one-out and temporal splits. |
| title | When and What to Recommend: Joint Modeling of Timing and Content for Active Sequential Recommendation |
| topic | Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2511.18717 |