Metraipolis › archive › dc_7db84db84a97

ChronicleRec: Pre-training Temporally Anchored Tokens for Lifelong User Modeling — arXiv:2609.12375

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.12375
License (as archived)
CC0-1.0
Archived
2026-10-16T03:57:15.650Z
SHA-256 of the archived text
53127e0fdb43e61799abe40e0fc1a34cde141f1d242a7fc5747a67a1dd02ba34
Stable URL of this page
https://metraipolis.com/documento/dc_7db84db84a97

How to cite

ChronicleRec: Pre-training Temporally Anchored Tokens for Lifelong User Modeling — arXiv:2609.12375 — arXiv (en), https://arxiv.org/abs/2609.12375 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7db84db84a97 (Metraipolis archive dc_7db84db84a97, sha256 53127e0fdb43e61799abe40e0fc1a34cde141f1d242a7fc5747a67a1dd02ba34)
BibTeX
@misc{dc7db84db84a97,
  title = {ChronicleRec: Pre-training Temporally Anchored Tokens for Lifelong User Modeling — arXiv:2609.12375},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12375},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7db84db84a97; sha256 53127e0fdb43e61799abe40e0fc1a34cde141f1d242a7fc5747a67a1dd02ba34},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12375. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modeling ultra-long user behavior sequences is crucial for industrial recommendation and online advertising, yet directly feeding thousands of historical actions into ranking models is computationally prohibitive, while truncation discards long-range signals. Existing lifelong-interest methods retrieve target-relevant behaviors for each candidate, coupling long-sequence modeling with candidate scoring and repeated online cost. Recent target-independent compression methods enable cached user summaries, but often append query tokens at the sequence end and use bidirectional encoding, producing unordered and redundant summaries that overlook temporal structure. We propose ChronicleRec, a pre-train-and-transfer framework that compresses an ultra-long behavior sequence once into a chronologically ordered set of Chronicle Tokens. ChronicleRec applies a recency-aware multi-granularity merge, preserving recent behaviors while coarsening distant history. It then interleaves query tokens with the merged sequence and uses a causal encoder, so each query summarizes only the history before its temporal anchor. A multi-horizon design masks different recent-history windows across parallel branches to learn complementary long-range interests. The compressor is pre-trained with a mask-and-predict objective that reconstructs held-out recent behaviors from compressed older history, aligning historical signals with near-present intent. Since Chronicle Tokens are target-independent, they can be cached per user, decoupling ultra-long sequence modeling from online candidate scoring. Experiments on KuaiRand and Tencent AdLive show that ChronicleRec outperforms recent-window and single-pass compression baselines while approaching full-attention performance. Token analyses reveal temporally organized and complementary representations, and a seven-day online A/B test confirms significant production gains.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-14 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.12375 — 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 2026-10-16T03:44:07.297Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).