English(EN) Efficient GPU Retrieval for Semantic Search

LinkedIn 推出新的用于语义搜索的 GPU 检索

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-01 04:00

研究人员在 LinkedIn 上开发了一种新的语义搜索检索框架，旨在提高用户个人资料建议的相关性。该系统将嵌入分割为八个类别监督段，从而能够更精确地匹配用户查询和相关个人资料。该方法采用 FP8 和 FP16 精度的两阶段 GPU 架构实现，显著提高了检索效率和准确性。在 A/B 测试中，新框架分别在探索性和导航性查询的 Precision@10 和 Precision@1 方面取得了显著改进。 AI

影响这项研究可能有助于在职业社交平台上实现更准确、更高效的个人资料匹配。

排序理由该条目是一篇详细介绍语义搜索新技术的学术论文，而非直接的产品发布公告。[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: 36 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该条目是一篇详细介绍语义搜索新技术的学术论文，而非直接的产品发布公告。[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, product; 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) · Dhritiman Das, Chujie Zheng, Ronak Kaoshik, Pratik Dixit, Vishal Shah, Yanbo Li, Jiahao Xu, Manika Agarwal, Chinmay Naik, Lingyu Zhang, Chetan Bhole, Chirag Bhanuprasad Mehta, Meng Zheng, Puneet Singh Ahluwalia, Shirisha Singh, Ping Jin, Manas Apte, Goku… · 2026-09-01 04:00

面向语义搜索的高效 GPU 检索

arXiv:2608.28968v1 Announce Type: new Abstract: Semantic Search on LinkedIn must retrieve relevant profiles from a corpus of hundreds of millions in response to natural-language queries such as "a fintech founder in Berlin who worked in payments." The deployed relevance policy is…

本文如何被排名

报道来源 [1]

面向语义搜索的高效 GPU 检索

相关实体

相关话题