{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T18:09:02Z","timestamp":1791396542006,"version":"4.3.3"},"reference-count":70,"publisher":"Association for Computing Machinery (ACM)","issue":"11","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2024,7]]},"abstract":"<jats:p>Human mobility data offers valuable insights for many applications such as urban planning and pandemic response, but its use also raises privacy concerns. In this paper, we introduce the Hierarchical and Multi-Resolution Network (HRNet), a novel deep generative model specifically designed to synthesize realistic human mobility data while guaranteeing differential privacy. We first identify the key difficulties inherent in learning human mobility data under differential privacy. In response to these challenges, HRNet integrates three components: a hierarchical location encoding mechanism, multi-task learning across multiple resolutions, and private pre-training. These elements collectively enhance the model's ability under the constraints of differential privacy. Through extensive comparative experiments utilizing a real-world dataset, HRNet demonstrates a marked improvement over existing methods in balancing the utility-privacy trade-off.<\/jats:p>","DOI":"10.14778\/3681954.3681983","type":"journal-article","created":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T12:23:36Z","timestamp":1725020616000},"page":"3058-3071","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["HRNet: Differentially Private Hierarchical and Multi-Resolution Network for Human Mobility Data Synthesization"],"prefix":"10.14778","volume":"17","author":[{"given":"Shun","family":"Takagi","sequence":"first","affiliation":[{"name":"Kyoto University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Xiong","sequence":"additional","affiliation":[{"name":"Emory University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fumiyuki","family":"Kato","sequence":"additional","affiliation":[{"name":"Kyoto University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Cao","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masatoshi","family":"Yoshikawa","sequence":"additional","affiliation":[{"name":"Osaka Seikei University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,30]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"e_1_2_1_2_1","unstructured":"Ritesh Ahuja Gabriel Ghinita and Cyrus Shahabi. 2020. Differentially-private next-location prediction with neural networks. In Advances in database technology. 121--132."},{"key":"e_1_2_1_3_1","volume-title":"International Conference on Machine Learning. PMLR, 517--535","author":"Amid Ehsan","year":"2022","unstructured":"Ehsan Amid, Arun Ganesh, Rajiv Mathews, Swaroop Ramaswamy, Shuang Song, Thomas Steinke, Vinith M Suriyakumar, Om Thakkar, and Abhradeep Thakurta. 2022. Public data-assisted mirror descent for private model training. In International Conference on Machine Learning. PMLR, 517--535."},{"key":"e_1_2_1_4_1","first-page":"4381","article-title":"Stability of stochastic gradient descent on nonsmooth convex losses","volume":"33","author":"Bassily Raef","year":"2020","unstructured":"Raef Bassily, Vitaly Feldman, Crist\u00f3bal Guzm\u00e1n, and Kunal Talwar. 2020. Stability of stochastic gradient descent on nonsmooth convex losses. Advances in Neural Information Processing Systems 33 (2020), 4381--4391.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_5_1","volume-title":"Private empirical risk minimization: Efficient algorithms and tight error bounds. In 2014 IEEE 55th annual symposium on foundations of computer science","author":"Bassily Raef","unstructured":"Raef Bassily, Adam Smith, and Abhradeep Thakurta. 2014. Private empirical risk minimization: Efficient algorithms and tight error bounds. In 2014 IEEE 55th annual symposium on foundations of computer science. IEEE, 464--473."},{"key":"e_1_2_1_6_1","volume-title":"Comparative study of differentially private data synthesis methods. Journal of Pivacy and Confidentiality 11-1","author":"McKay Bowen Claire","year":"2021","unstructured":"Claire McKay Bowen and Fang Liu. 2021. Comparative study of differentially private data synthesis methods. Journal of Pivacy and Confidentiality 11-1 (2021), 280--307."},{"key":"e_1_2_1_7_1","unstructured":"USC Bureau. 2020. On the map: Longitudinal employer-household dynamics https:\/\/lehd.ces.census.gov\/applications\/help\/onthemap.html#confidentiality_protection."},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3130978"},{"key":"e_1_2_1_9_1","volume-title":"Jaline Gerardin, Beth Redbird, David Grusky, and Jure Leskovec.","author":"Chang Serina","year":"2021","unstructured":"Serina Chang, Emma Pierson, Pang Wei Koh, Jaline Gerardin, Beth Redbird, David Grusky, and Jure Leskovec. 2021. Mobility network models of COVID-19 explain inequities and inform reopening. Nature 589, 7840 (2021), 82--87."},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2382196.2382263"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2011.07.035"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2016.140952"},{"key":"e_1_2_1_14_1","unstructured":"Bolin Ding Janardhan Kulkarni and Sergey Yekhanin. 2017. Collecting telemetry data privately. In Advances in Neural Information Processing Systems. 3571--3580."},{"key":"e_1_2_1_15_1","volume-title":"Differentially private diffusion models. arXiv preprint arXiv:2210.09929","author":"Dockhorn Tim","year":"2022","unstructured":"Tim Dockhorn, Tianshi Cao, Arash Vahdat, and Karsten Kreis. 2022. Differentially private diffusion models. arXiv preprint arXiv:2210.09929 (2022)."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/11787006_1"},{"key":"e_1_2_1_17_1","volume-title":"Theory of cryptography conference","author":"Dwork Cynthia","unstructured":"Cynthia Dwork, Frank McSherry, Kobbi Nissim, and Adam Smith. 2006. Calibrating noise to sensitivity in private data analysis. In Theory of cryptography conference. Springer, 265--284."},{"key":"e_1_2_1_18_1","first-page":"3","article-title":"The algorithmic foundations of differential privacy","volume":"9","author":"Dwork Cynthia","year":"2014","unstructured":"Cynthia Dwork, Aaron Roth, et al. 2014. The algorithmic foundations of differential privacy. Foundations and Trends in Theoretical Computer Science 9, 3--4 (2014), 211--407.","journal-title":"Foundations and Trends in Theoretical Computer Science"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2660267.2660348"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186058"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3412862"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3260981"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2018.2874008"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.14778\/2809974.2809978"},{"key":"e_1_2_1_25_1","volume-title":"Long short-term memory. Neural computation 9, 8","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735--1780."},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2023.104315"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2015.7218422"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3187009.3177733"},{"key":"e_1_2_1_29_1","volume-title":"Conference on Learning Theory. PMLR, 2717--2746","author":"Kairouz Peter","year":"2021","unstructured":"Peter Kairouz, Monica Ribero Diaz, Keith Rush, and Abhradeep Thakurta. 2021. (Nearly) Dimension Independent Private ERM with AdaGrad Rates via Publicly Estimated Subspaces. In Conference on Learning Theory. PMLR, 2717--2746."},{"key":"e_1_2_1_30_1","volume-title":"International conference on machine learning. PMLR, 1376--1385","author":"Kairouz Peter","year":"2015","unstructured":"Peter Kairouz, Sewoong Oh, and Pramod Viswanath. 2015. The composition theorem for differential privacy. In International conference on machine learning. PMLR, 1376--1385."},{"key":"e_1_2_1_31_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 2560--2569","author":"Koskela Antti","year":"2020","unstructured":"Antti Koskela, Joonas J\u00e4lk\u00f6, and Antti Honkela. 2020. Computing tight differential privacy guarantees using fft. In International Conference on Artificial Intelligence and Statistics. PMLR, 2560--2569."},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2017.03.015"},{"key":"e_1_2_1_33_1","volume-title":"DPSyn: Experiences in the NIST Differential Privacy Data Synthesis Challenges. Journal of Privacy and Confidentiality 11-2","author":"Li Ninghui","year":"2021","unstructured":"Ninghui Li, Zhikun Zhang, and Tianhao Wang. 2021. DPSyn: Experiences in the NIST Differential Privacy Data Synthesis Challenges. Journal of Privacy and Confidentiality 11-2 (2021)."},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1463434.1463477"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403252"},{"key":"e_1_2_1_36_1","volume-title":"Learning and inferring transportation routines. Artificial intelligence 171, 5--6","author":"Liao Lin","year":"2007","unstructured":"Lin Liao, Donald J Patterson, Dieter Fox, and Henry Kautz. 2007. Learning and inferring transportation routines. Artificial intelligence 171, 5--6 (2007), 311--331."},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531989"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411876"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011020"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00152"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115120"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485125"},{"key":"e_1_2_1_44_1","volume-title":"STAN: Spatio-Temporal Attention Network for next Point-of-Interest Recommendation. WWW. 2177\u015b2185","author":"Luo Yingtao","year":"2021","unstructured":"Yingtao Luo, Qiang Liu, and Zhaocheng Liu. 2021. STAN: Spatio-Temporal Attention Network for next Point-of-Interest Recommendation. WWW. 2177\u015b2185 (2021)."},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2008.4497436"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compenvurbsys.2023.101938"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.56553\/popets-2023-0065"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/MDM58254.2023.00044"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-04771-9_10"},{"key":"e_1_2_1_50_1","volume-title":"Privacy loss classes: The central limit theorem in differential privacy. Cryptology ePrint Archive","author":"Sommer David","year":"2018","unstructured":"David Sommer, Sebastian Meiser, and Esfandiar Mohammadi. 2018. Privacy loss classes: The central limit theorem in differential privacy. Cryptology ePrint Archive (2018)."},{"key":"e_1_2_1_51_1","volume-title":"Except-Condition Generative Adversarial Network for Generating Trajectory Data. In International Conference on Database and Expert Systems Applications. Springer, 289--294","author":"Song Yeji","year":"2023","unstructured":"Yeji Song, Jihwan Shin, Jinhyun Ahn, Taewhi Lee, and Dong-Hyuk Im. 2023. Except-Condition Generative Adversarial Network for Generating Trajectory Data. In International Conference on Database and Expert Systems Applications. Springer, 289--294."},{"key":"e_1_2_1_52_1","volume-title":"31st USENIX Security Symposium (USENIX Security 22)","author":"Stadler Theresa","year":"2022","unstructured":"Theresa Stadler, Bristena Oprisanu, and Carmela Troncoso. 2022. Synthetic data-anonymisation groundhog day. In 31st USENIX Security Symposium (USENIX Security 22). 1451--1468."},{"key":"e_1_2_1_53_1","volume-title":"HRNet: Differentially Private Hierarchical and Multi-Resolution Network for Human Mobility Data Synthesization. arXiv:2405.08043","author":"Takagi Shun","year":"2024","unstructured":"Shun Takagi, Li Xiong, Fumiyuki Kato, Yang Cao, and Masatoshi Yoshikawa. 2024. HRNet: Differentially Private Hierarchical and Multi-Resolution Network for Human Mobility Data Synthesization. arXiv:2405.08043 (2024). https:\/\/arxiv.org\/abs\/2308.12210"},{"key":"e_1_2_1_54_1","unstructured":"A. D. P. Team. 2017. Learning with privacy at scale."},{"key":"e_1_2_1_55_1","volume-title":"A computer movie simulating urban growth in the Detroit region. Economic geography 46, sup1","author":"Tobler Waldo R","year":"1970","unstructured":"Waldo R Tobler. 1970. A computer movie simulating urban growth in the Detroit region. Economic geography 46, sup1 (1970), 234--240."},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2018.2829173"},{"key":"e_1_2_1_57_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_2_1_58_1","volume-title":"USENIX Security Symposium","author":"Wang Haiming","year":"2023","unstructured":"Haiming Wang, Zhikun Zhang, Tianhao Wang, Shibo He, Michael Backes, Jiming Chen, and Yang Zhang. 2023. PrivTrace: Differentially Private Trajectory Synthesis by Adaptive Markov Model. In USENIX Security Symposium 2023."},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3025580"},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.14778\/3574245.3574277"},{"key":"e_1_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi6020057"},{"key":"e_1_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591770"},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/302"},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/2676552.2676557"},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3134428"},{"key":"e_1_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2882928"},{"key":"e_1_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/MDM58254.2023.00032"},{"key":"e_1_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/1658373.1658374"},{"key":"e_1_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/1526709.1526816"},{"key":"e_1_2_1_70_1","volume-title":"Zhiwei Steven Wu, and Arindam Banerjee","author":"Zhou Yingxue","year":"2021","unstructured":"Yingxue Zhou, Zhiwei Steven Wu, and Arindam Banerjee. 2021. Bypassing the Ambient Dimension: Private SGD with Gradient Subspace Identification. ICLR abs\/2007.03813 (2021). https:\/\/api.semanticscholar.org\/CorpusID:220404588"}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/3681954.3681983","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T14:43:28Z","timestamp":1725461008000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/3681954.3681983"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":70,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["10.14778\/3681954.3681983"],"URL":"https:\/\/doi.org\/10.14778\/3681954.3681983","relation":{},"ISSN":["2150-8097"],"issn-type":[{"value":"2150-8097","type":"print"}],"subject":[],"published":{"date-parts":[[2024,7]]},"assertion":[{"value":"2024-08-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}