English(EN) Zero-Observation User Reactivation with Gap-Driven Dimensional Gating

新的DeltaGate方法解决了推荐系统中的零观测用户再激活问题

作者 PulseAugur 编辑部 · [3 个来源] · 2026-07-22 06:32

研究人员开发了一种名为DeltaGate的新方法，以解决顺序推荐系统中零观测用户再激活的挑战。该方法旨在使用一种由差距驱动的维度门控机制，重新吸引长时间未与平台互动的用户。DeltaGate通过根据上次互动以来的时间差距，在用户的历史数据和学习到的全局先验之间路由表示维度来工作。 AI

影响这项研究可以通过有效重新吸引休眠用户来改善推荐系统中的用户参与度。

排序理由该集群包含一篇详细介绍顺序推荐系统新方法的论文。

AI 生成摘要 · Google Gemini · 来自 3 个来源。我们如何撰写摘要 →

报道来源 [3]

arXiv cs.LG TIER_1 English(EN) · Jiandong Ding, Tianying Liu, Fuyuan Liu, Huijie Qin, Tiandeng Wu · 2026-07-23 04:00

零样本用户再激活：基于差距驱动的维度门控

arXiv:2607.19802v1 Announce Type: cross Abstract: Sequential recommendation (SR) models capture continuously observed behavior, but a returning user may have no interactions for months or years. We define this setting as Zero-Observation Reactivation: the user has a pre-gap histo…
arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Tiandeng Wu · 2026-07-22 06:32

零样本用户再激活：基于间隙驱动的维度门控

Sequential recommendation (SR) models capture continuously observed behavior, but a returning user may have no interactions for months or years. We define this setting as Zero-Observation Reactivation: the user has a pre-gap history, while the platform observes no behavioral sign…
Hugging Face Daily Papers TIER_1 English(EN) · 2026-07-22 06:32

零样本用户再激活：基于间隔驱动的维度门控

Sequential recommendation (SR) models capture continuously observed behavior, but a returning user may have no interactions for months or years. We define this setting as Zero-Observation Reactivation: the user has a pre-gap history, while the platform observes no behavioral sign…