Abstract
Many machine learning problems, such as medical data summarization and social welfare maximization, can be modeled as the problems of maximizing monotone submodular functions. Differentially private submodular functions under cardinality constraints are first proposed and studied to solve the Combinatorial Public Projects (CPP) problem, in order to protect personal data privacy while processing sensitive data. However, the research of these functions for privacy protection has received little attention so far. In this paper, we propose to study the differentially private submodular maximization problem over the integer lattice. Our main contributions are to present differentially private approximation algorithms for both DR-submodular and integer submodular function maximization problems under cardinality constraints and analyze the sensitivity of our algorithms.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Agrawal, R., Squires, C., Yang, K., Shanmugam, K., Uhler, C.: Abcd-strategy: budgeted experimental design for targeted causal structure discovery. In: Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, pp. 3400–3409 (2019)
Bian, Y., Buhmann, J., Krause, A.: Optimal continuous DR-submodular maximization and applications to provable mean field inference. In: Proceedings of the 36th International Conference on Machine Learning, pp. 644–653 (2020)
Bian, A., Levy, K., Krause, A., Buhmann, J. M.: Non-monotone continuous DR-submodular maximization: Structure and algorithms. In: Proceedings of the 30th Annual Conference on Neural Information Processing Systems, pp. 486–496 (2017)
Chaturvedi, A., Nguy\(\tilde{\hat{e}}\)n, H. L., Zakynthinou, L.: Differentially private decomposable submodular maximization. In: Proceedings of the 35th AAAI Conference on Artificial Intelligence, pp. 6984–6992 (2021)
Chen, L., Hassani, H., Karbasi, A.: Online continuous submodular maximization. In: Proceedings of the 21st International Conference on Artificial Intelligence and Statistics, pp. 1896–1905 (2018)
Gupta, A., Ligett, K., McSherry, F., Roth, A., Talwar, K.: Differentially private combinatorial optimization. In: Proceedings of the 21st Annual ACM-SIAM Symposium on Discrete Algorithms, pp. 1106–1125 (2010)
Krause, A., Smith, D., Crawford, V.G., Thai, M.T.: Fast maximization of non-submodular, monotonic functions on integer lattice. In: Proceedings of the 35th International Conference on Machine Learning, pp. 2791–2800 (2018)
McSherry, F., Talwar, K.: Mechanism design via differential privacy. In: Proceedings of the 48th Annual IEEE Symposium on Foundations of Computer Science, pp. 94–103 (2007)
Mitrovic, M., Bun, M., Krause, A., Karbasi, A.: Differentially private submodular maximization: Data summarization in disguise. In: Proceedings of the 34th International Conference on Machine Learning, pp. 2478–2487 (2017)
Nong, Q., Fang, J., Gong, S., Du, D., Feng, Y., Qu, X.: A 1/2-approximation algorithm for maximizing a non-monotone weak-submodular function on a bounded integer lattice. J. Comb. Optim. 39(4), 1208–1220 (2020). https://doi.org/10.1007/s10878-020-00558-4
Qian, C., Yu, Y., Zhou, Z.H.: Subset selection by pareto optimization. In: Proceedings of the 28th Annual Conference on Neural Information Processing Systems, pp. 1765–1773 (2015)
Qian, C., Zhang, Y., Tang, K., Yao, X.: On multiset selection with size constraints. In: Proceedings of the 32nd AAAI Conference on Artificial Intelligence, pp. 1395–1402 (2018)
Rafiey, A., Yoshida, Y.: Fast and private submodular and \(k\)-submodular functions maximization with matroid constraints. In: Proceedings of the 37th International Conference on Machine Learning, pp. 7887–7897 (2020)
Sahin, A., Buhmann, J.M., Krause, A.: Constrained maximization of lattice submodular functions. IN: ICML 2020 workshop on Negative Dependence and Submodularity for ML, Vienna, Austria, PMLR 119 (2020)
Sahin, A., Bian, Y., Buhmann, J.M., Krause, A.: From sets to multisets: provable variational inference for probabilistic integer submodular models. In: Proceedings of the 37th International Conference on Machine Learning, pp. 8388–8397 (2020)
Soma, T., Kakimura, N., Inaba, K., Kawarabayashi, K.: Optimal budget allocation: theoretical guarantee and efficient algorithm. In: Proceedings of the 31st International Conference on Machine Learning, pp. 351–359 (2014)
Soma, T., Yoshida, Y.: A generalization of submodular cover via the diminishing return property on the integer lattice. In: Proceedings of Advances in Neural Information Processing Systems, pp. 847–855 (2015)
Soma, T., Yoshida, Y.: Non-monotone DR-submodular function maximization. In: Proceedings of the 31st AAAI conference on Artificial Intelligence, pp. 898–904 (2017)
Soma, T., Yoshida, Y.: Maximizing monotone submodular functions over the integer lattice. Math. Program. 172(4), 539–563 (2018). https://doi.org/10.1007/s10107-018-1324-y
Tan, J., Zhang, D., Zhang, H., Zhang, Z.: Streaming algorithms for monotone DR-submodular maximization under a knapsack constraint on the integer lattice. In: Ning, L., Chau, V., Lau, F. (eds.) PAAP 2020. CCIS, vol. 1362, pp. 58–67. Springer, Singapore (2021). https://doi.org/10.1007/978-981-16-0010-4_6
Zhang, Z., Guo, L., Wang, L., Zou, J.: A streaming model for monotone lattice submodular maximization with a cardinality constraint. In: Proceedings of the 21st International Conference on Parallel and Distributed Computing, Applications and Technlolgies, pp. 362–370 (2020)
Acknowledgements
The first two authors are supported by National Natural Science Foundation of China (No. 12131003) and Beijing Natural Science Foundation Project No. Z200002. The third author is supported by National Natural Sciences and Engineering Research Council of Canada (NSERC) grant 06446, and National Natural Science Foundation of China (Nos. 11771386, 11728104). The fourth author is supported by the Province Natural Science Foundation of Shandong (No. ZR2017MA031) and the National Natural Science Foundation of China (No. 11801310).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Hu, J., Xu, D., Du, D., Miao, C. (2021). Differentially Private Submodular Maximization over Integer Lattice. In: Mohaisen, D., Jin, R. (eds) Computational Data and Social Networks. CSoNet 2021. Lecture Notes in Computer Science(), vol 13116. Springer, Cham. https://doi.org/10.1007/978-3-030-91434-9_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-91434-9_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-91433-2
Online ISBN: 978-3-030-91434-9
eBook Packages: Computer ScienceComputer Science (R0)