Distributed data deduplication

Abstract

Data deduplication refers to the process of identifying tuplets in a relation that refers to the same real world entity. The complexity of the problem is inherently quadratic with respect to the number of tuples, since a similarity value must be computed for every pair of tuples. In order to avoid comparing tuple pairs that are obviously non-duplicates, matching algorithms using blocking techniques that divide the tuples into blocks and compare only tuples within the same block. However, even with the use of blocking, data deduplication remains a costly problem for large datasets. In this paper, we show how to further speed up data deduplication by leveraging parallelism in a shared-nothing computing environment. Our main contribution is a distribution strategy, called \disdedup, that minimizes the maximum workload across all worker nodes and provides strong theoretical guarantees. We demonstrate the effectiveness of our proposed strategy by performing extensive experiments on both synthetic datasets with varying block size distributions, as well as real world datasets.