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

Approximate nearest neighbor (ANN) search is a fundamental problem in areassuch as data management,information retrieval and machine learning. Recently,Li et al. proposed a learned approach named AdaptNN to support adaptive ANNquery processing. In the middle of query execution, AdaptNN collects a numberof runtime features and predicts termination condition for each individualquery, by which better end-to-end latency is attained. Despite its efficiency,using runtime features complicates the learning process and leads toperformance degradation. Radically different from AdaptNN, we argue that it ispromising to predict termination condition before query exetution.Particularly, we developed Tao, a general learning framework for TerminatingANN queries Adaptively using Only static features. Upon the arrival of a query,Tao first maps the query to a local intrinsic dimension (LID) number, and thenpredicts the termination condition using LID instead of runtime features. Bydecoupling prediction procedure from query execution, Tao eliminates thelaborious feature selection process involved in AdaptNN. Besides, two designprinciples are formulated to guide the application of Tao and improve theexplainability of the prediction model. We integrate two state-of-the-artindexing approaches, i.e., IMI and HNSW, into Tao, and evaluate the performanceover several million to billion-scale datasets. Experimental results show that,in addition to its simplicity and generality , Tao achieves up to 2.69x speedupeven compared to its counterpart, at the same high accuracy targets.

Tao: A Learning Framework for Adaptive Nearest Neighbor Search using Static Features Only