Abstract
Linkage of records that refer to the same entity across different databases finds applications in several areas, including healthcare, business, national security, and government services. In the absence of unique identifiers, quasi-identifiers (e.g. name, age, address) must be used to identify records of the same entity in different databases. These quasi-identifiers (QIDs) contain personal identifiable information (PII). Therefore, record linkage must be conducted in a way that preserves privacy. Using Cryptographic Long-term Key (CLK)-based encoding is one popular privacy-preserving record linkage (PPRL) technique where different QIDs are encoded independently into a representation that preserves records’ similarity but obscures PII. To achieve accurate results, the parameters of a CLK encoding must be tuned to suit the data. To this end, we study a Bayesian optimization method for effectively tuning hyper-parameters for CLK-based PPRL. Moreover, ground-truth labels (match or non-match) would be useful for evaluating linkage quality in the optimization, but they are often difficult to access. We address this by proposing an unsupervised method that uses heuristics to estimate linkage quality. Finally, we investigate the information leakage risk with the iterative approach of optimization methods and discuss recommendations to mitigate the risk. Experimental results show that our method requires fewer iterations to achieve good linkage results compared to two baseline optimization methods. It not only improves linkage quality and computational efficiency of hyper-parameter optimization, but also reduces the privacy risk.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
Available from ftp://dl.ncsbe.gov/data/.
- 2.
The source code is available in http://doi.org/10.5281/zenodo.3971263.
References
Bergstra, J.S., Bardenet, R., Bengio, Y., Kégl, B.: Algorithms for hyper-parameter optimization. In: Advances in Neural Information Processing Systems, pp. 2546–2554 (2011)
Borgs, C.: Optimal parameter choice for bloom filter-based privacy-preserving record linkage. Ph.D. thesis (2019). https://doi.org/10.17185/duepublico/70274
Brown, A.P., Randall, S.M., Boyd, J.H., Ferrante, A.M.: Evaluation of approximate comparison methods on bloom filters for probabilistic linkage. Int. J. Popul. Data Sci. 4(1) (2019)
Christen, P., Ranbaduge, T., Vatsalan, D., Schnell, R.: Precise and fast cryptanalysis for Bloom filter based privacy-preserving record linkage. IEEE Trans. Knowl. Data Eng. 31, 2164–2177 (2018)
CSIRO’s Data61: Anonlink private record linkage system (2017). https://github.com/data61/clkhash
Kuehni, C.E., et al.: Cohort profile: the Swiss childhood cancer survivor study. Int. J. Epidemiol. 41(6), 1553–1564 (2011)
Randall, S.M., Ferrante, A.M., Boyd, J.H., Semmens, J.B.: Privacy-preserving record linkage on large real world datasets. J. Biomed. Inform. 50(1), 1 (2014)
Schnell, R.: Privacy preserving record linkage. In: Harron, K., Goldstein, H., Dibben, C. (eds.) Methodological Developments in Data Linkage, pp. 201–225. Wiley, Chichester (2016)
Schnell, R., Bachteler, T., Reiher, J.: A novel error-tolerant anonymous linking code. German Record Linkage Center, Working Paper Series No. WP-GRLC-2011-02 (2011)
Snoek, J., Larochelle, H., Adams, R.P.: Practical Bayesian optimization of machine learning algorithms. In: Advances in Neural Information Processing Systems, pp. 2951–2959 (2012)
Vatsalan, D., Christen, P.: Privacy-preserving matching of similar patients. J. Biomed. Inform. 59, 285–298 (2016)
Vatsalan, D., Christen, P., O’Keefe, C.M., Verykios, V.S.: An evaluation framework for privacy-preserving record linkage. J. Priv. Confid. 6(1), 1 (2014)
Vatsalan, D., Christen, P., Rahm, E.: Scalable privacy-preserving linking of multiple databases using counting Bloom filters. In: Workshop on Privacy and Discrimination in Data Mining held at IEEE ICDM, Barcelona (2016)
Vatsalan, D., Christen, P., Verykios, V.S.: A taxonomy of privacy-preserving record linkage techniques. Inf. Syst. 38(6), 946–969 (2013)
Acknowledgements
This work was funded by the Australian Department of Social Sciences (DSS) as part of the Platforms for Open Data (PfOD) project. We would like to thank Waylon Nielsen, Alex Ware, and Maruti Vadrevu from DSS for their support and feedback on this work.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Yu, J., Nabaglo, J., Vatsalan, D., Henecka, W., Thorne, B. (2020). Hyper-Parameter Optimization for Privacy-Preserving Record Linkage. In: Koprinska, I., et al. ECML PKDD 2020 Workshops. ECML PKDD 2020. Communications in Computer and Information Science, vol 1323. Springer, Cham. https://doi.org/10.1007/978-3-030-65965-3_18
Download citation
DOI: https://doi.org/10.1007/978-3-030-65965-3_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-65964-6
Online ISBN: 978-3-030-65965-3
eBook Packages: Computer ScienceComputer Science (R0)