{"id":795491,"date":"2021-11-16T08:00:54","date_gmt":"2021-11-16T16:00:54","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&#038;p=795491"},"modified":"2021-11-16T12:53:11","modified_gmt":"2021-11-16T20:53:11","slug":"research-talk-approximate-nearest-neighbor-search-systems-at-scale","status":"publish","type":"msr-video","link":"https:\/\/www.microsoft.com\/en-us\/research\/video\/research-talk-approximate-nearest-neighbor-search-systems-at-scale\/","title":{"rendered":"Research talk: Approximate nearest neighbor search systems at scale"},"content":{"rendered":"<p>Building deep learning-based search and recommendation systems at internet scale requires a complete redesign of the search index. Key to this redesign is a fast, accurate, and cost-efficient indexing system for approximate nearest neighbor search. In this talk, we\u2019ll present our recent advances in this space, including the DiskANN and FreshDiskANN systems and the underlying algorithms. These algorithms present an order-of-magnitude improvement in scale and cost-of-operation over the state of the art and are a first of their kind at effectively using solid-state drives (SSDs) to serve at interactive (milliseconds) latencies. In addition, they provide faster in-memory search than other graph indices, like HNSW, and support real-time concurrent insertions and deletions to SSD-resident indices without losing recall. We\u2019ll provide an overview their applicability to various product scenarios and highlight directions for further research.<\/p>\n<p>Learn more about the 2021 Microsoft Research Summit: <a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/Aka.ms\/researchsummit\">https:\/\/Aka.ms\/researchsummit<span class=\"sr-only\"> (opens in new tab)<\/span><\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Building deep learning-based search and recommendation systems at internet scale requires a complete redesign of the search index. Key to this redesign is a fast, accurate, and cost-efficient indexing system for approximate nearest neighbor search. In this talk, we\u2019ll present our recent advances in this space, including the DiskANN and FreshDiskANN systems and the underlying [&hellip;]<\/p>\n","protected":false},"featured_media":795494,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"research-area":[13561,13556,13560,13555,13547],"msr-video-type":[261263,261302],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-795491","msr-video","type-msr-video","status-publish","has-post-thumbnail","hentry","msr-research-area-algorithms","msr-research-area-artificial-intelligence","msr-research-area-programming-languages-software-engineering","msr-research-area-search-information-retrieval","msr-research-area-systems-and-networking","msr-video-type-research-summit-2021","msr-video-type-the-future-of-search-recommendation","msr-locale-en_us"],"msr_download_urls":"","msr_external_url":"https:\/\/youtu.be\/BnYNdSIKibQ","msr_secondary_video_url":"","msr_video_file":"","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/795491"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-video"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/795491\/revisions"}],"predecessor-version":[{"id":795497,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/795491\/revisions\/795497"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/795494"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=795491"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=795491"},{"taxonomy":"msr-video-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video-type?post=795491"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=795491"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=795491"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=795491"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}