Set2Box: Similarity Preserving Representation Learning of Sets

TL;DR

Set2Box introduces a learning-based set representation method using boxes that enables fast, accurate similarity estimation with reduced storage, outperforming traditional hashing and sketching techniques.

Contribution

The paper presents Set2Box and Set2Box+ methods for representing sets as boxes, allowing efficient similarity computation and improved accuracy over baseline approaches.

Findings

Set2Box+ achieves up to 40.8X smaller estimation error.

Set2Box+ requires 60% fewer bits for encoding.

The approach enables estimation of four similarity measures from one representation.

Abstract

Sets have been used for modeling various types of objects (e.g., a document as the set of keywords in it and a customer as the set of the items that she has purchased). Measuring similarity (e.g., Jaccard Index) between sets has been a key building block of a wide range of applications, including, plagiarism detection, recommendation, and graph compression. However, as sets have grown in numbers and sizes, the computational cost and storage required for set similarity computation have become substantial, and this has led to the development of hashing and sketching based solutions. In this work, we propose Set2Box, a learning-based approach for compressed representations of sets from which various similarity measures can be estimated accurately in constant time. The key idea is to represent sets as boxes to precisely capture overlaps of sets. Additionally, based on the proposed box quantization scheme, we design Set2Box+, which yields more concise but more accurate box representations of sets. Through extensive experiments on 8 real-world datasets, we show that, compared to baseline approaches, Set2Box+ is (a) Accurate: achieving up to 40.8X smaller estimation error while requiring 60% fewer bits to encode sets, (b) Concise: yielding up to 96.8X more concise representations with similar estimation error, and (c) Versatile: enabling the estimation of four set-similarity measures from a single representation of each set.