English(EN) misi: a Metric Inverted Sample Index

新的度量倒排样本索引 (misi) 用于高效的 ANN 搜索

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-27 17:48

研究人员开发了一种名为 misi（度量倒排样本索引）的新数据结构，旨在用于度量空间中高效的近似最近邻搜索。该索引使用数据库的随机样本作为其词汇表，并通过其最近的样本点来表示每个对象。其构建过程高度可并行化且内存效率高，使其适用于构建成本和内存占用至关重要的频繁重建语料库和批量相似性工作负载。 AI

影响引入了一种用于近似最近邻搜索的新型索引，有可能提高 AI 相关相似性任务的效率。

排序理由该集群包含一篇详细介绍信息检索新数据结构的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

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: 6 / 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信息检索新数据结构的学术论文。[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: paper, infra; 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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Edgar Chavez · 2026-08-27 17:48

misi: 一个度量反转样本索引

We present misi, an inverted index for approximate nearest-neighbor search over general metric spaces whose vocabulary is a random sample of the database, of size proportional to $n$. Each object is represented by its $k_b$ nearest sample points, found by a pluggable inner index …