Lune

ICLR2025Top-tier venue

Temporal Heterogeneous Graph Generation with Privacy, Utility, and Efficiency

Xinyu He, Dongqi Fu, Hanghang Tong, Ross Maciejewski, Jingrui He

Abstract

Nowadays, temporal heterogeneous graphs attract much research and industrial attention for building the next-generation Relational Deep Learning models and applications, due to their informative structures and features. While providing timely and precise services like personalized recommendations and question answering, this rich information also introduces extra exposure risk for each node in the graph. The distinctive local topology, the abundant heterogeneous features, and the time dimension of the graph data are more prone to expose sensitive information and narrow down the scope of victim candidates, which calls for welldefined protection techniques on graphs. To this end, we propose a Temporal Heterogeneous Graph Generator balancing Privacy, Utility, and Efficiency, named THEPUFF. More specifically, we first propose a differential privacy algorithm to perturb the input temporal heterogeneous graph for protecting privacy, and then utilize both the perturbed graph and the original one in a generative adversarial setting for THEPUFF to learn and generate privacy-guaranteed and utility-preserved graph data in an efficient manner. We further propose 6 new metrics in the temporal setting to measure heterogeneous graph utility and privacy. Finally, based on temporal heterogeneous graph datasets with up to 1 million nodes and 20 million edges, the experiments show that THEPUFF generates utilizable temporal heterogeneous graphs with privacy protected, compared with state-of-the-art baselines.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

7 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • GDGB: A Benchmark for Generative Dynamic Text-Attributed Graph Learning cites A Data-Driven Graph Generative Model for Temporal Interaction Networks
  • OwlEye: Zero-Shot Learner for Cross-Domain Graph Data Anomaly Detection cites A Data-Driven Graph Generative Model for Temporal Interaction Networks
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers7

  1. HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic RelationsShuaicheng Zhang, Haohui Wang, Junhong Lin, Xiaojie Guo et al.NeurIPS 2025 · 5 citations
  2. GDGB: A Benchmark for Generative Dynamic Text-Attributed Graph LearningJie Peng, Jiarui Ji, Runlin Lei, Zhewei Wei et al.ICLR 2026 · 4 citations
  3. DRGW: Learning Disentangled Representations for Robust Graph WatermarkingJiasen Li, Yanwei Liu, Zhuoyi Shang, Xiaoyan Gu et al.WWW 2026 · 3 citations
  4. OwlEye: Zero-Shot Learner for Cross-Domain Graph Data Anomaly DetectionLecheng Zheng, Dongqi Fu, Zihao Li, Jingrui HeICLR 2026 · 2 citations
  5. Geometric Constraints for Small Language Models to Understand and Expand Scientific TaxonomiesLiri Fang, Dongqi Fu, Jiawei Han, Jingrui He et al.ICLR 2026

Builds on18

  1. TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale UpYifan Jiang, Shiyu Chang, Zhangyang WangNeurIPS 2021 · 515 citations
  2. Antigen-Specific Antibody Design and Optimization with Diffusion-Based Generative Models for Protein StructuresShitong Luo, Yufeng Su, Xingang Peng, Sheng Wang et al.NeurIPS 2022 · 331 citations
  3. Generating Synthetic Decentralized Social Graphs with Local Differential PrivacyZhan Qin, Ting Yu, Yin Yang, Issa Khalil et al.CCS 2017 · 266 citations
  4. Diffusion-based Molecule Generation with Informative Prior BridgesLemeng Wu, Chengyue Gong, Xingchao Liu, Mao Ye et al.NeurIPS 2022 · 165 citations
  5. A Data-Driven Graph Generative Model for Temporal Interaction NetworksDawei Zhou, Lecheng Zheng, Jiawei Han, Jingrui HeKDD 2020 · 97 citations

Related papers

  1. Neural Graph Generation from Graph StatisticsKiarash Zahirnia, Yaochen Hu, Mark Coates, Oliver SchulteNeurIPS 2023 · 4 citations
  2. PrivGraph: Differentially Private Graph Data Publication by Exploiting Community InformationQuan Yuan, Zhikun Zhang, Linkang Du, Min Chen et al.USENIX Security 2023
  3. Achieving Personalized Privacy-Preserving Graph Neural Network via Topology AwarenessDian Lei, Zijun Song, Yanli Yuan, Chunhai Li et al.WWW 2025 · 6 citations
  4. PrivAGS: Differentially Private Attributed Graph SynthesisShuzhan Ye, Lu Chen, Zhikun Zhang, Yunjun Gao et al.SIGMOD 2026
  5. P 2 FedRec: Towards Privacy-Preserving and Personalized Federated Recommendation via Relationship AwarenessChenfei Hu, Zihao Xu, Tong Wu, You Li et al.SIGMOD 2026 · 3 citations
Dusk over the sea between two cliffs drawn in fine vertical lines