Add to ORKGDespite the efficacy of graph-based algorithms for Approximate Nearest Neighbor (ANN) searches, the optimal tuning of such systems remains unclear. This study introduces a method to tune the performance of off-the-shelf graph-based indexes, focusing on the dimension of vectors, database size, and entry points of graph traversal. We utilize a black-box optimization algorithm to perform integrated tuning to meet the required levels of recall and Queries Per Second (QPS). We applied our approach to Task A of the SISAP 2023 Indexing Challenge and got second place in the 10M and 30M tracks. It improves performance substantially compared to brute force methods. This research offers a universally applicable tuning method for graph-based indexes, e...
Unlike tree indicators used in current works, our index responds to less effectiveness in order to i...
The ability to extract or retrieve useful knowledge has become one of the most important challenges ...
For free-text search over rapidly evolving corpora, dynamic update of inverted indices is a basic re...
A fast response is critical in many data-intensive applications, including knowledge discovery analy...
The last decade brought considerable improvements in dis - tributed storage and query t...
Learned Indexes use a model to restrict the search of a sorted table to a smaller interval. Typicall...
The performance issues are presented. The process of performance tuning is described. The indexing c...
Approximate nearest neighbor algorithms are used to speed up nearest neighbor search in a wide array...
Learned Indexes are a novel approach to search in a sorted table. A model is used to predict an inte...
n the presence of growing data, the need for efficient query processing under result quality and ind...
Cataloged from PDF version of article.In recent times, large high-dimensional datasets have become u...
International audienceSimilarity search approaches based on graph walks have recently attained outst...
Graph data management systems have become very popular as graphs are the natural data model for man...
With the surging popularity of approximate near-neighbor search (ANNS), driven by advances in neural...
In this article, we present an efficient B + -tree based indexing method, ca...
Unlike tree indicators used in current works, our index responds to less effectiveness in order to i...
The ability to extract or retrieve useful knowledge has become one of the most important challenges ...
For free-text search over rapidly evolving corpora, dynamic update of inverted indices is a basic re...
A fast response is critical in many data-intensive applications, including knowledge discovery analy...
The last decade brought considerable improvements in dis - tributed storage and query t...
Learned Indexes use a model to restrict the search of a sorted table to a smaller interval. Typicall...
The performance issues are presented. The process of performance tuning is described. The indexing c...
Approximate nearest neighbor algorithms are used to speed up nearest neighbor search in a wide array...
Learned Indexes are a novel approach to search in a sorted table. A model is used to predict an inte...
n the presence of growing data, the need for efficient query processing under result quality and ind...
Cataloged from PDF version of article.In recent times, large high-dimensional datasets have become u...
International audienceSimilarity search approaches based on graph walks have recently attained outst...
Graph data management systems have become very popular as graphs are the natural data model for man...
With the surging popularity of approximate near-neighbor search (ANNS), driven by advances in neural...
In this article, we present an efficient B + -tree based indexing method, ca...
Unlike tree indicators used in current works, our index responds to less effectiveness in order to i...
The ability to extract or retrieve useful knowledge has become one of the most important challenges ...
For free-text search over rapidly evolving corpora, dynamic update of inverted indices is a basic re...