Metraipolis › archive › dc_c19d74a5e039

SITA: Semantic Interest Tokens for Target-Aware Compression in Long-Sequence Recommendation — arXiv:2608.03692

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.03692
License (as archived): CC0-1.0
Archived: 2026-10-31T12:57:52.210Z
SHA-256 of the archived text: 63e1125f7cd6646c79368a234c912779165a62c710fad469df9cebd25b245152
Stable URL of this page: https://metraipolis.com/documento/dc_c19d74a5e039

How to cite

SITA: Semantic Interest Tokens for Target-Aware Compression in Long-Sequence Recommendation — arXiv:2608.03692 — arXiv (en), https://arxiv.org/abs/2608.03692 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c19d74a5e039 (Metraipolis archive dc_c19d74a5e039, sha256 63e1125f7cd6646c79368a234c912779165a62c710fad469df9cebd25b245152)

BibTeX

@misc{dcc19d74a5e039,
  title = {SITA: Semantic Interest Tokens for Target-Aware Compression in Long-Sequence Recommendation — arXiv:2608.03692},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03692},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c19d74a5e039; sha256 63e1125f7cd6646c79368a234c912779165a62c710fad469df9cebd25b245152},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03692. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As user behavior histories continue to grow on modern Internet platforms, effectively modeling long behavior sequences has become crucial for predicting user interests in candidate items. Existing methods have evolved along two directions. One line dynamically retrieves target-relevant behaviors from long histories, enabling target-aware modeling but requiring target-dependent computation during inference. The other line compresses entire behavior sequences into compact user representations, achieving high efficiency and scalability but sacrificing target-specific adaptation due to target-independent encoding. The key challenge is therefore to enable target-aware modeling while preserving the efficiency and scalability of compressed user representations. To address this challenge, we propose \textbf{SITA}, a target-aware compression framework for long-sequence recommendation. SITA enables target-aware compression by organizing compressed interests into semantic structures through semantic identifiers learned via parallel semantic quantization. Conditioned on the semantic identifier of the target item, SITA adaptively aggregates the corresponding structured interests to construct the target-specific user representation. Extensive experiments on public datasets and a large-scale industrial dataset demonstrate that SITA consistently outperforms representative baselines while maintaining strong scalability, highlighting its strong potential for real-world recommender systems.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-05 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2608.03692 — 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 2026-10-31T12:45:13.295Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).