Horizontal Multi-Party Data Publishing Under Differential Privacy via Weight-Aware Bidirectional Generative Adversarial Networks
- 9 April 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (8) , 5142-5158
Abstract
Horizontal multi-party data publishing enables parties with the same attributes but different records to collaboratively share synthetic data. Generative adversarial networks (GAN) excel at capturing complex distributions and generating statistically consistent samples. However, existing studies treat all parties' data equally without considering heterogeneity, approximate data distributions largely from only a single direction, and suffer from training instability under limited privacy budgets. To address these limitations, we propose MASTER, a weight-aware bidirectional GAN approach. In MASTER, each party maintains a sanitized discriminator to protect local data, while a central server coordinates two complementary generators that learn the underlying data distribution from different perspectives. Specifically, we introduce a dual-generator GAN structure, where training is enhanced by simultaneously increasing the distance between the distributions of generated samples to improve diversity and reducing the discriminators' ability to distinguish them to stabilize training and enhance sample quality. Moreover, a weight-aware fusion mechanism is designed to dynamically balance contributions from different parties and generators based on data quality, enhancing inter-party connections, generation diversity, and training stability. To compute the weights, we formulate an unsupervised integer programming problem and design an alternating optimization scheme. Our theoretical analysis demonstrates that MASTER maintains comparable computational complexity to non-private settings while providing strong differential privacy and utility guarantees. Extensive experiments on four real-world datasets and one synthetic dataset show MASTER's effectiveness.Keywords
Funding Information
- Natural Science Research Project of Anhui Educational Committee (2024AH050364)
This publication has 23 references indexed in Scilit:
- A two-phase approach for locally differentially private fuzzy co-clusteringInformation Sciences, 2025
- Horizontal multi-party data publishing via discriminator regularization and adaptive noise under differential privacyInformation Fusion, 2025
- WF-LDPSR: A local differential privacy mechanism based on water-filling for secure release of trajectory statistics dataComputers & Security, 2024
- In-Distribution Public Data Synthesis With Diffusion Models for Differentially Private Image Classification2024
- Marginal Release Under Multi-party Personalized Differential Privacy2023
- GAN-based Differential Privacy Trajectory Data Publishing with Sensitive Label2022
- Pricing GAN-based data generators under Rényi differential privacyInformation Sciences, 2022
- Private FL-GAN: Differential Privacy Synthetic Data Generation Based on Federated Learning2020
- Heterogeneous differential privacy for vertically partitioned databasesConcurrency and Computation: Practice and Experience, 2019
- Rényi Differential Privacy2017