mlsanityData to 7 Oct 2026

Gromov-Wasserstein Discrepancy with Local Differential Privacy for Distributed Structural Graphs

arXiv 2202.00808 ↗First posted 1 Feb 2022cs.LG cs.CRcited by 6

Not on the map. Why?

Abstract (arXiv)

Learning the similarity between structured data, especially the graphs, is one of the essential problems. Besides the approach like graph kernels, Gromov-Wasserstein (GW) distance recently draws big attention due to its flexibility to capture both topological and feature characteristics, as well as handling the permutation invariance. However, structured data are widely distributed for different data mining and machine learning applications. With privacy concerns, accessing the decentralized data is limited to either individual clients or different silos. To tackle these issues, we propose a privacy-preserving framework to analyze the GW discrepancy of node embedding learned locally from graph neural networks in a federated flavor, and then explicitly place local differential privacy (LDP) based on Multi-bit Encoder to protect sensitive information. Our experiments show that, with strong privacy protections guaranteed by the varepsilon-LDP algorithm, the proposed framework not only preserves privacy in graph learning but also presents a noised structural metric under GW distance, resulting in comparable and even better performance in classification and clustering tasks. Moreover, we reason the rationale behind the LDP-based GW distance analytically and empirically.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 27 of its 65 references that are in the map. First posted on arXiv 1 Feb 2022.

Builds on

27 of 65 references.

References · 27

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  6. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  7. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
  8. 2019Graph Neural Networks for Social Recommendationcited by 711
  9. 2017Federated Multi-Task Learningcited by 669
  10. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 493
  11. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
  12. 2020FedML: A Research Library and Benchmark for Federated Machine Learningcited by 298
15 more
  1. 2017How to Escape Saddle Points Efficientlycited by 284
  2. 2020Permutation Invariant Graph Generation via Score-Based Generative Modelingcited by 263
  3. 2016Practical Secure Aggregation for Federated Learning on User-Held Datacited by 178
  4. 2018Optimal Transport for structured data with application on graphscited by 170
  5. 2018RSA: Byzantine-Robust Stochastic Aggregation Methods for Distributed Learning from Heterogeneous Datasetscited by 148
  6. 2019Gromov-Wasserstein Learning for Graph Matching and Node Embeddingcited by 125
  7. 2018Gromov-Wasserstein Alignment of Word Embedding Spacescited by 119
  8. 2019Scalable Gromov-Wasserstein Learning for Graph Partitioning and Matchingcited by 102
  9. 2020Byzantine-Resilient Secure Federated Learningcited by 93
  10. 2019Accelerating Federated Learning via Momentum Gradient Descentcited by 75
  11. 2020Locally Private Graph Neural Networkscited by 64
  12. 2020GraphFL: A Federated Learning Framework for Semi-Supervised Node Classification on Graphscited by 64
  13. 2020Information Obfuscation of Graph Neural Networkscited by 19
  14. 2021FL-AGCNS: Federated Learning Framework for Automatic Graph Convolutional Network Searchcited by 8
  15. 2019Privacy-Utility Tradeoffs in Routing Cryptocurrency over Payment Channel Networkscited by 1

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 3; 2024: 1.

6 papers.

  1. 2022Degree-Preserving Randomized Response for Graph Neural Networks under Local Differential Privacycited by 7
  2. 2023Decentralized Graph Neural Network for Privacy-Preserving Recommendationcited by 3
  3. 2023Privacy-Preserving Graph Embedding based on Local Differential Privacycited by 3
  4. 2024Wasserstein Differential Privacycited by 3
  5. 2022Mitigating the Performance Sacrifice in DP-Satisfied Federated Settings through Graph Contrastive Learningcited by 2
  6. 2023Optimal Transport for Kernel Gaussian Mixture Modelscited by 0