English(EN) Orthogonal Norm Growth in Two-Tower Retrieval: A Popularity Mechanism for Unified Discovery

研究探讨范数增长作为统一发现系统中流行度机制

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-06 10:47

一篇新研究论文探讨了在结合搜索和推荐的统一发现系统中，正交范数增长如何充当流行度机制。该研究侧重于这些系统中物品向量的重复更新如何增加其范数，从而影响检索性能，特别是在未归一化点积计算下。在MovieLens 32M和Amazon Books等数据集上的实验表明，物品向量中累积的切线移动与频率范数关联以及在使用原始点积排序时增加头部物品曝光率相关。 AI

排序理由一篇在arXiv上发表的研究论文，详细介绍了一种新颖的检索机制。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.IR (Information Retrieval) 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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 一篇在arXiv上发表的研究论文，详细介绍了一种新颖的检索机制。[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: 5 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Andrei Atamaniuk · 2026-11-06 10:47

双塔检索中的正交范数增长：统一发现的热门机制

Unified search and recommendation systems may update the same item vectors from both interaction streams. We study how repeated updates can increase an item vector's norm and affect retrieval under an unnormalized dot product. A cosine-only loss makes the output gradient perpendi…

本文如何被排名

报道来源 [1]

双塔检索中的正交范数增长：统一发现的热门机制

相关实体

相关话题