Metraipolis › archive › dc_118de0bced6e

H2CE: Modeling Geo-Semantic Interactions for POI Reranking with Heterogeneous Two-Stage Cross-Encoders — arXiv:2610.11277

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.11277
License (as archived)
CC0-1.0
Archived
2026-10-09T06:29:57.491Z
SHA-256 of the archived text
066fe02806cdec7b2b22545257b187421214859564b80bb290d27aff9f63a0d2
Stable URL of this page
https://metraipolis.com/documento/dc_118de0bced6e

How to cite

H2CE: Modeling Geo-Semantic Interactions for POI Reranking with Heterogeneous Two-Stage Cross-Encoders — arXiv:2610.11277 — arXiv (en), https://arxiv.org/abs/2610.11277 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_118de0bced6e (Metraipolis archive dc_118de0bced6e, sha256 066fe02806cdec7b2b22545257b187421214859564b80bb290d27aff9f63a0d2)
BibTeX
@misc{dc118de0bced6e,
  title = {H2CE: Modeling Geo-Semantic Interactions for POI Reranking with Heterogeneous Two-Stage Cross-Encoders — arXiv:2610.11277},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.11277},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_118de0bced6e; sha256 066fe02806cdec7b2b22545257b187421214859564b80bb290d27aff9f63a0d2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11277. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Point-of-Interest (POI) reranking in local search must model query-conditioned tradeoffs among lexical semantics, geospatial proximity, and numerical quality signals such as rating and review count, while remaining practical under real-time serving constraints. A close POI may only partially satisfy the query intent, while a farther one may offer stronger semantic and quality evidence. We present H2CE, a Heterogeneous Two-stage Cross-Encoder for latency-bounded POI reranking. H2CE represents numerical attributes in two complementary ways: bucketized natural-language descriptors are inserted into the cross-encoder input to support semantic--numeric attention, while exact scalar values are processed by dedicated MLPs to preserve magnitude information. The resulting semantic and numerical embeddings are fused through latent-space aggregation, enabling nonlinear interactions beyond scalar weighted sums. H2CE then applies a two-stage architecture: Stage 1 scores all candidates pointwise for scalable filtering, and Stage 2 performs head-to-head pairwise comparison among the top-$K$ candidates with Copeland aggregation, making fine-grained relative tradeoffs explicit while reducing pairwise cost from O(N^2) to O(N+K(K-1)). On a 5,743-query local search test set, H2CE achieves 67.48% NDCG@5, improving over XGBoost LTR by +22.82% absolute and over a zero-shot LLM reranker by +35.89%. The pairwise stage adds +1.98% NDCG@5 over the pointwise model alone. Ablations confirm the value of numerical features, latent aggregation, top-K pairwise reranking, and aligned training.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.IR, nuovi lavori del giorno).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2610.11277 — 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 2026-10-09T05:54:51.496Z dalla pagina https://arxiv.org/list/cs.IR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).