DiskJoin: Large-scale Vector Similarity Join with SSD

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Yanqi, Yan, Xiao, Meliou, Alexandra, Lo, Eric
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917002569842688
author Chen, Yanqi
Yan, Xiao
Meliou, Alexandra
Lo, Eric
author_facet Chen, Yanqi
Yan, Xiao
Meliou, Alexandra
Lo, Eric
contents Similarity join--a widely used operation in data science--finds all pairs of items that have distance smaller than a threshold. Prior work has explored distributed computation methods to scale similarity join to large data volumes but these methods require a cluster deployment, and efficiency suffers from expensive inter-machine communication. On the other hand, disk-based solutions are more cost-effective by using a single machine and storing the large dataset on high-performance external storage, such as NVMe SSDs, but in these methods the disk I/O time is a serious bottleneck. In this paper, we propose DiskJoin, the first disk-based similarity join algorithm that can process billion-scale vector datasets efficiently on a single machine. DiskJoin improves disk I/O by tailoring the data access patterns to avoid repetitive accesses and read amplification. It also uses main memory as a dynamic cache and carefully manages cache eviction to improve cache hit rate and reduce disk retrieval time. For further acceleration, we adopt a probabilistic pruning technique that can effectively prune a large number of vector pairs from computation. Our evaluation on real-world, large-scale datasets shows that DiskJoin significantly outperforms alternatives, achieving speedups from 50x to 1000x.
format Preprint
id arxiv_https___arxiv_org_abs_2508_18494
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DiskJoin: Large-scale Vector Similarity Join with SSD
Chen, Yanqi
Yan, Xiao
Meliou, Alexandra
Lo, Eric
Databases
Similarity join--a widely used operation in data science--finds all pairs of items that have distance smaller than a threshold. Prior work has explored distributed computation methods to scale similarity join to large data volumes but these methods require a cluster deployment, and efficiency suffers from expensive inter-machine communication. On the other hand, disk-based solutions are more cost-effective by using a single machine and storing the large dataset on high-performance external storage, such as NVMe SSDs, but in these methods the disk I/O time is a serious bottleneck. In this paper, we propose DiskJoin, the first disk-based similarity join algorithm that can process billion-scale vector datasets efficiently on a single machine. DiskJoin improves disk I/O by tailoring the data access patterns to avoid repetitive accesses and read amplification. It also uses main memory as a dynamic cache and carefully manages cache eviction to improve cache hit rate and reduce disk retrieval time. For further acceleration, we adopt a probabilistic pruning technique that can effectively prune a large number of vector pairs from computation. Our evaluation on real-world, large-scale datasets shows that DiskJoin significantly outperforms alternatives, achieving speedups from 50x to 1000x.
title DiskJoin: Large-scale Vector Similarity Join with SSD
topic Databases
url https://arxiv.org/abs/2508.18494