Improving Locality Sensitive Hashing by Efficiently Finding Projected Nearest Neighbors

Jafari, Omid; Nagarkar, Parth; Montaño, Jonathan

doi:10.1007/978-3-030-60936-8_25

Cited by 9 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main idea behind LSH is that the points that are close in the original space will map to the same hash buckets in the low-dimensional spaces with a higher probability compared to the points that are far from each other in the original space. Since LSH is used in many different applications [8], there have been several works that have been proposed to improve its accuracy and performance [16,5,7,3,10,12,13,9,15].…”

Section: Locality Sensitive Hashingmentioning

confidence: 99%

“…Hence, LSH is a useful technique in many applications where data independency and scalability are important. While the traditional LSH index structures suffered from disk I/Os, novel index structures, such as roLSH [9], have been proposed to improve the disk I/Os, and thus, the performance of LSH. To improve the disk I/Os (specifically, the random disk I/Os), roLSH utilizes machine learning techniques to predict the search radius before beginning query processing.…”

Section: Motivationmentioning

confidence: 99%

“…As mentioned in Section 2, LSH methods that use Virtual Rehashing in the query processing, start the search with an initial radius of 1 and if not enough candidates are found, then the radius is increased in an exponential fashion. roLSH [9], shows that the exponential increase of the radius is not efficient and leads to excessive disk I/Os; thus, roLSH proposes an improved index structure that uses sampling and machine learning techniques to predict the optimized radius for a given query. Although roLSH provides novel techniques to fix errors in the predicted radius, its performance and accuracy can be affected by the chosen machine learning technique.…”

Section: Problem Specificationmentioning

confidence: 99%

See 2 more Smart Citations

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

Jafari¹,

Nagarkar²

2022

Preprint

View full text Add to dashboard Cite

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 Networkbased 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.

show abstract