English(EN) HyperPage: Learned Page Layouts for Disk-Resident Graph Vector Indexes

HyperPage 使用学习布局优化磁盘驻留图向量索引

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-12 01:21

研究人员开发了 HyperPage，一种优化磁盘驻留图向量索引的新颖方法。与 Starling 和 MARGO 等之前的布局不同，HyperPage 利用强化学习和搜索代理遍历的日志来创建针对特定内存预算量身定制的页面布局。该方法旨在通过智能地将记录及其关联的图边分组到 SSD 页面上来最小化页面读取次数。测试表明，在各种缓存预算下，HyperPage 与 MARGO 相比，页面读取次数减少了 5.2% 至 21.2%，在较小的缓存尺寸下改进最为显著。 AI

影响这项研究可能导致更高效的大型向量数据集存储和检索，从而影响依赖于相似性搜索的 AI 应用。

排序理由这是一篇详细介绍优化数据结构新方法的学术论文。[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: 1 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇详细介绍优化数据结构新方法的学术论文。[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: infra, paper; 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: 1 days old; Coverage has settled into its steady-state 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) · Weiwei Sun · 2026-11-12 01:21

HyperPage: 面向磁盘驻留图向量索引的学习页面布局

Disk-resident graph indexes such as DiskANN store each vector with its graph edges as one record on SSD pages. A search needs the page of every record it expands, so its page reads depend on the page layout, that is, which records share a page. Search agents trained with reinforc…

本文如何被排名

报道来源 [1]

HyperPage: 面向磁盘驻留图向量索引的学习页面布局

相关实体

相关话题