English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Given a vector dataset $\mathcal{X}$ and a query vector $\vec{x}_q$,graph-based Approximate Nearest Neighbor Search (ANNS) aims to build a graphindex $G$ and approximately return vectors with minimum distances to$\vec{x}_q$ by searching over $G$. The main drawback of graph-based ANNS isthat a graph index would be too large to fit into the memory especially for alarge-scale $\mathcal{X}$. To solve this, a Product Quantization (PQ)-basedhybrid method called DiskANN is proposed to store a low-dimensional PQ index inmemory and retain a graph index in SSD, thus reducing memory overhead whileensuring a high search accuracy. However, it suffers from two I/O issues thatsignificantly affect the overall efficiency: (1) long routing path from anentry vertex to the query's neighborhood that results in large number of I/Orequests and (2) redundant I/O requests during the routing process. We proposean optimized DiskANN++ to overcome above issues. Specifically, for the firstissue, we present a query-sensitive entry vertex selection strategy to replaceDiskANN's static graph-central entry vertex by a dynamically determined entryvertex that is close to the query. For the second I/O issue, we present anisomorphic mapping on DiskANN's graph index to optimize the SSD layout andpropose an asynchronously optimized Pagesearch based on the optimized SSDlayout as an alternative to DiskANN's beamsearch. Comprehensive experimentalstudies on eight real-world datasets demonstrate our DiskANN++'s superiority onefficiency. We achieve a notable 1.5 X to 2.2 X improvement on QPS compared toDiskANN, given the same accuracy constraint.

DiskANN++: Efficient Page-based Search over Isomorphic Mapped Graph Index using Query-sensitivity Entry Vertex