Experimental Analysis of Machine Learning Techniques for Finding Search Radius in Locality Sensitive Hashing

TL;DR

This paper evaluates various Machine Learning methods to optimize the search radius in Locality Sensitive Hashing, demonstrating that Neural Network-based techniques offer the best accuracy-performance balance for high-dimensional data retrieval.

Contribution

It extends the radius-optimized LSH (roLSH) by experimentally analyzing the impact of different ML techniques, identifying Neural Networks as the most effective.

Findings

Neural Network-based ML techniques outperform others in accuracy and speed.

Experimental results on four real-world datasets support the superiority of Neural Networks.

The study provides guidance for selecting ML methods to enhance LSH performance.

Abstract

Finding similar data in high-dimensional spaces is one of the important tasks in multimedia applications. Approaches introduced to find exact searching techniques often use tree-based index structures which are known to suffer from the curse of the dimensionality problem that limits their performance. Approximate searching techniques prefer performance over accuracy and they return good enough results while achieving a better performance. Locality Sensitive Hashing (LSH) is one of the most popular approximate nearest neighbor search techniques for high-dimensional spaces. One of the most time-consuming processes in LSH is to find the neighboring points in the projected spaces. An improved LSH-based index structure, called radius-optimized Locality Sensitive Hashing (roLSH) has been proposed to utilize Machine Learning and efficiently find these neighboring points; thus, further improve the overall performance of LSH. In this paper, we extend roLSH by experimentally studying the effect of different types of famous Machine Learning techniques on overall performance. We compare ten regression techniques on four real-world datasets and show that Neural Network-based techniques are the best fit to be used in roLSH as their accuracy and performance trade-off are the best compared to the other techniques.