Metraipolis › archive › dc_9529f41df5d2
SPAR: Enhancing Industrial-Scale Generative POI Recommendation via Real-World Spatial Perception — arXiv:2609.02062
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.02062
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T05:46:45.218Z
- SHA-256 of the archived text
541f6da0cd620194b48f897ae7e810be1ad386a62702b7fb8cf6c8aef81e09cf- Stable URL of this page
https://metraipolis.com/documento/dc_9529f41df5d2
How to cite
SPAR: Enhancing Industrial-Scale Generative POI Recommendation via Real-World Spatial Perception — arXiv:2609.02062 — arXiv (en), https://arxiv.org/abs/2609.02062 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9529f41df5d2 (Metraipolis archive dc_9529f41df5d2, sha256 541f6da0cd620194b48f897ae7e810be1ad386a62702b7fb8cf6c8aef81e09cf)
BibTeX
@misc{dc9529f41df5d2,
title = {SPAR: Enhancing Industrial-Scale Generative POI Recommendation via Real-World Spatial Perception — arXiv:2609.02062},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.02062},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9529f41df5d2; sha256 541f6da0cd620194b48f897ae7e810be1ad386a62702b7fb8cf6c8aef81e09cf},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02062. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generative Point-of-Interest (POI) recommendation, autoregressively generating a target POI's semantic ID (SID), holds great promise for Location-Based Services, where a recommendation helps only if the user can reach it. Yet, existing methods operate within an interest space defined by behavior sequences and collaborative signals, where geography enters only as a textual attribute of the SID, leaving no explicit mechanism to learn or preserve how urban places are related by distance, direction, and reachability; their predictions are thus behaviorally plausible yet far from the user's real-time location. We argue that such services require injecting real urban spatial knowledge into the interest space, rather than inferring geography from behavior alone. Hence, we propose SPAR, a unified framework whose three synergistic stages jointly construct, cultivate, and preserve urban spatial knowledge: (1) at the tokenization level, Spatially-Intrinsic SID (SI-SID) explicitly encodes longitude--latitude coordinates into a sinusoidal geospatial embedding and fuses it with the textual semantic embedding, producing identifiers via RQ-Kmeans that are simultaneously semantically and geographically consistent; (2) at the cognition level, Multi-Granular Geospatial CPT (MG-CPT) continually pre-trains the base LLM on 25 curated geospatial datasets organized into three tiers of basic attributes, pairwise relations, and city-scale navigation, so that scattered POIs cohere into a connected urban space; and (3) at the adaptation level, Task-Vector Anchored SFT (TV-SFT) anchors the acquired spatial knowledge as a frozen parameter-space task vector to prevent its catastrophic forgetting during behavioral fine-tuning, thereby fusing the two spaces. Extensive quantitative and visualization experiments on two public and four industrial-scale datasets demonstrate the effectiveness of SPAR. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-03 in cs.IR). Categorie arXiv: Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2609.02062 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T05:23:20.836Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).