English(EN) MARS: Multi-resolution Adaptive Routing for Sequential Recommendation

MARS系统改进了长历史序列推荐

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-07 04:00

研究人员开发了MARS，一种新颖的序列推荐系统方法，旨在更有效地处理长用户历史。MARS解决了“时间别名”问题，即传统方法难以同时表示短暂意图、中期兴趣和长期偏好。通过使用多分辨率用户记忆和稀疏路由阅读器，MARS保留相关的时间分辨率，为候选评分生成紧凑的种子记忆，在多个数据集上，尤其是在处理更长历史时，其表现优于现有基线。 AI

影响提高了具有丰富互动历史的用户的推荐准确性。

排序理由该集群包含一篇详细介绍序列推荐系统新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 15 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍序列推荐系统新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Ming Yin, Sixun Dong, Yudong Liu, Wen-Yun Yang, Yunjiang Jiang, Yiran Chen · 2026-10-07 04:00

MARS：多分辨率自适应路由用于序列推荐

arXiv:2610.07505v1 Announce Type: new Abstract: Long-history recommenders often compress each user's history into a compact, candidate-independent memory that is cached and reused to score large candidate pools. We show that real user histories exhibit multi-scale semantic struct…

本文如何被排名

报道来源 [1]

MARS：多分辨率自适应路由用于序列推荐

相关实体

相关话题