Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

8-2023

Abstract

Entity Resolution (ER) is a fundamental problem in data preparation. Standard deep ER methods have achieved state-of-the-art efectiveness, assuming that relations from diferent organizations are centrally stored. However, due to privacy concerns, it can be difcult to centralize data in practice, rendering standard deep ER solutions inapplicable. Despite eforts to develop rule-based privacy-preserving ER methods, they often neglect subtle matching mechanisms and have poor efectiveness as a result. To bridge efectiveness and privacy, in this paper, we propose CampER, an efective framework for privacy-aware deep entity resolution. Specifcally, we frst design a training pair self-generation strategy to overcome the absence of manually labeled data in privacy-aware scenarios. Based on the selfconstructed training pairs, we present a collaborative fne-tuning approach to learn the match-aware and uni-space individual tuple embeddings for accurate matching decisions. During the matching decision-making process, we frst introduce a cryptographically secure approach to determine matches. Furthermore, we propose an order-preserving perturbation strategy to signifcantly accelerate the matching computation while guaranteeing the consistency of ER results. Extensive experiments on eight widely-used benchmark datasets demonstrate that CampER not only is comparable with the state-of-the-art standard deep ER solutions in efectiveness, but also preserves privacy.

Keywords

entity resolution, representation learning, similarity measurement

Discipline

Databases and Information Systems

Research Areas

Data Science and Engineering

Publication

KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Long Beach, CA, August 6-10

First Page

626

Last Page

637

ISBN

9798400701030

Identifier

10.1145/3580305.3599266

Publisher

ACM

City or Country

New York

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1145/3580305.3599266

Share

COinS