ADS-POI: Agentic Spatiotemporal State Decomposition for Next Point-of-Interest Recommendation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915950360526848 |
|---|---|
| author | Yu, Zhenyu Meng, Chunlei Zeng, Yangchen Idris, Mohd Yamani Idna Zhou, Shuigeng |
| author_facet | Yu, Zhenyu Meng, Chunlei Zeng, Yangchen Idris, Mohd Yamani Idna Zhou, Shuigeng |
| contents | Next point-of-interest (POI) recommendation requires modeling user mobility as a spatiotemporal sequence, where different behavioral factors may evolve at different temporal and spatial scales. Most existing methods compress a user's history into a single latent representation, which tends to entangle heterogeneous signals such as routine mobility patterns, short-term intent, and temporal regularities. This entanglement limits the flexibility of state evolution and reduces the model's ability to adapt to diverse decision contexts. We propose ADS-POI, a spatiotemporal state decomposition framework for next POI recommendation. ADS-POI represents a user with multiple parallel evolving latent sub-states, each governed by its own spatiotemporal transition dynamics. These sub-states are selectively aggregated through a context-conditioned mechanism to form the decision state used for prediction. This design enables different behavioral components to evolve at different rates while remaining coordinated under the current spatiotemporal context. Extensive experiments on three real-world benchmark datasets from Foursquare and Gowalla demonstrate that ADS-POI consistently outperforms strong state-of-the-art baselines under a full-ranking evaluation protocol. The results show that decomposing user behavior into multiple spatiotemporally aware states leads to more effective and robust next POI recommendation. Our code is available at https://github.com/YuZhenyuLindy/ADS-POI.git. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_20846 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ADS-POI: Agentic Spatiotemporal State Decomposition for Next Point-of-Interest Recommendation Yu, Zhenyu Meng, Chunlei Zeng, Yangchen Idris, Mohd Yamani Idna Zhou, Shuigeng Information Retrieval Artificial Intelligence Next point-of-interest (POI) recommendation requires modeling user mobility as a spatiotemporal sequence, where different behavioral factors may evolve at different temporal and spatial scales. Most existing methods compress a user's history into a single latent representation, which tends to entangle heterogeneous signals such as routine mobility patterns, short-term intent, and temporal regularities. This entanglement limits the flexibility of state evolution and reduces the model's ability to adapt to diverse decision contexts. We propose ADS-POI, a spatiotemporal state decomposition framework for next POI recommendation. ADS-POI represents a user with multiple parallel evolving latent sub-states, each governed by its own spatiotemporal transition dynamics. These sub-states are selectively aggregated through a context-conditioned mechanism to form the decision state used for prediction. This design enables different behavioral components to evolve at different rates while remaining coordinated under the current spatiotemporal context. Extensive experiments on three real-world benchmark datasets from Foursquare and Gowalla demonstrate that ADS-POI consistently outperforms strong state-of-the-art baselines under a full-ranking evaluation protocol. The results show that decomposing user behavior into multiple spatiotemporally aware states leads to more effective and robust next POI recommendation. Our code is available at https://github.com/YuZhenyuLindy/ADS-POI.git. |
| title | ADS-POI: Agentic Spatiotemporal State Decomposition for Next Point-of-Interest Recommendation |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2604.20846 |