HRNet: Differentially Private Hierarchical and Multi-Resolution Network for Human Mobility Data Synthesization

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Takagi, Shun, Xiong, Li, Kato, Fumiyuki, Cao, Yang, Yoshikawa, Masatoshi
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929428337000448
author Takagi, Shun
Xiong, Li
Kato, Fumiyuki
Cao, Yang
Yoshikawa, Masatoshi
author_facet Takagi, Shun
Xiong, Li
Kato, Fumiyuki
Cao, Yang
Yoshikawa, Masatoshi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_08043
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle HRNet: Differentially Private Hierarchical and Multi-Resolution Network for Human Mobility Data Synthesization
Takagi, Shun
Xiong, Li
Kato, Fumiyuki
Cao, Yang
Yoshikawa, Masatoshi
Cryptography and Security
Machine Learning
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.
title HRNet: Differentially Private Hierarchical and Multi-Resolution Network for Human Mobility Data Synthesization
topic Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2405.08043