mlsanityData to 7 Oct 2026

HoGS: Homophily-Oriented Graph Synthesis for Local Differentially Private GNN Training

arXiv 2602.08762 ↗First posted 9 Feb 2026cs.LG cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) have demonstrated remarkable performance in various graph-based machine learning tasks by effectively modeling high-order interactions between nodes. However, training GNNs without protection may leak sensitive personal information in graph data, including links and node features. Local differential privacy (LDP) is an advanced technique for protecting data privacy in decentralized networks. Unfortunately, existing local differentially private GNNs either only preserve link privacy or suffer significant utility loss in the process of preserving link and node feature privacy. In this paper, we propose an effective LDP framework, called HoGS, which trains GNNs with link and feature protection by generating a synthetic graph. Concretely, HoGS first collects the link and feature information of the graph under LDP, and then utilizes the phenomenon of homophily in graph data to reconstruct the graph structure and node features separately, thereby effectively mitigating the negative impact of LDP on the downstream GNN training. We theoretically analyze the privacy guarantee of HoGS and conduct experiments using the generated synthetic graph as input to various state-of-the-art GNN architectures. Experimental results on three real-world datasets show that HoGS significantly outperforms baseline methods in the accuracy of training GNNs.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 42 references that are in the map. First posted on arXiv 9 Feb 2026.

Builds on

23 of 42 references.

References · 23

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  5. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  6. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
  7. 2014RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Responsecited by 262
  8. 2021Graph Neural Network for Traffic Forecasting: A Surveycited by 260
  9. 2017Collecting Telemetry Data Privatelycited by 147
  10. 2020Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Modelscited by 116
  11. 2021LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysiscited by 65
  12. 2020Locally Private Graph Neural Networkscited by 64
11 more
  1. 2022GAP: Differentially Private Graph Neural Networks with Aggregation Perturbationcited by 46
  2. 2018Beyond One-hot Encoding: lower dimensional target embeddingcited by 42
  3. 2017Towards Practical Differential Privacy for SQL Queriescited by 19
  4. 2020Locally Differentially Private Analysis of Graph Statisticscited by 17
  5. 2022Towards Private Learning on Decentralized Graphs with Local Differential Privacycited by 16
  6. 2023PrivGraph: Differentially Private Graph Data Publication by Exploiting Community Informationcited by 13
  7. 2022LPGNet: Link Private Graph Networks for Node Classificationcited by 12
  8. 2022Degree-Preserving Randomized Response for Graph Neural Networks under Local Differential Privacycited by 7
  9. 2023Blink: Link Local Differential Privacy in Graph Neural Networks via Bayesian Estimationcited by 6
  10. 2022Differentially Private Triangle and 4-Cycle Counting in the Shuffle Modelcited by 5
  11. 2025ICGNN: Graph Neural Network Enabled Scalable Beamforming for MISO Interference Channelscited by 1

Built on by

Not cited yet.