Metraipolis › archive › dc_c8b69e03bc7b
GateDiffInt: Gate-Mediated Controllable Diffusion and Multi-Intent LLM Distillation for User Behavior Modeling — arXiv:2608.18764
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.18764
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T14:03:41.982Z
- SHA-256 of the archived text
7af74eccceca70df931a76f9beb6ac51bbfea419011dd6972451e95c84549747- Stable URL of this page
https://metraipolis.com/documento/dc_c8b69e03bc7b
How to cite
GateDiffInt: Gate-Mediated Controllable Diffusion and Multi-Intent LLM Distillation for User Behavior Modeling — arXiv:2608.18764 — arXiv (en), https://arxiv.org/abs/2608.18764 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c8b69e03bc7b (Metraipolis archive dc_c8b69e03bc7b, sha256 7af74eccceca70df931a76f9beb6ac51bbfea419011dd6972451e95c84549747)
BibTeX
@misc{dcc8b69e03bc7b,
title = {GateDiffInt: Gate-Mediated Controllable Diffusion and Multi-Intent LLM Distillation for User Behavior Modeling — arXiv:2608.18764},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.18764},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c8b69e03bc7b; sha256 7af74eccceca70df931a76f9beb6ac51bbfea419011dd6972451e95c84549747},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18764. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Existing ranking models encode intent only implicitly, making it hard to disentangle structured intents of varying strength and temporal scale. Noise and intent in behavior sequences are mutually reinforcing---we call this Noise--Intent Coupling (NIC). Noise dilutes true intents, while the lack of structured intent priors leaves denoising without a clear target. To address NIC, we propose GateDiffInt, an intent interaction framework for industrial ranking. It uses the final conversion signal to jointly align sequence denoising and intent extraction. GateDiffInt applies a controllable forward diffusion process with dual gating to enhance and denoise behavior sequences. A large language model then acts as teacher to distill four structured intents---long-term, short-term, latent, and conversion into a lightweight student model. The enhanced sequence and structured intent representations are deeply fused via attention to produce intent-aware representations for conversion-rate prediction. Extensive experiments on public and large-scale industrial datasets show consistent gains over strong baselines. In online A/B tests serving hundreds of millions of daily active users, GateDiffInt delivers substantial GMV improvements and has been deployed to primary traffic, confirming both effectiveness and production readiness. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-20 in cs.IR). Categorie arXiv: Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2608.18764 — 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 2026-10-18T13:59:46.170Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).