# Privacy-preserving design of graph neural networks with applications to vertical federated learning

arXiv: https://arxiv.org/abs/2310.20552 · HTML: https://mlsanity.com/paper/2310.20552/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 54 references that are in the map.
- First posted on arXiv 31 Oct 2023.

## Builds on (most cited first, 16 of 16)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Gated Graph Sequence Neural Networks](https://mlsanity.com/paper/1511.05493/) (2015)
- [Vertical Federated Learning: Concepts, Advances and Challenges](https://mlsanity.com/paper/2211.12814/) (2022)
- [FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendation](https://mlsanity.com/paper/2102.04925/) (2021)
- [VAFL: a Method of Vertical Asynchronous Federated Learning](https://mlsanity.com/paper/2007.06081/) (2020)
- [LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysis](https://mlsanity.com/paper/2108.06504/) (2021)
- [Vertically Federated Graph Neural Network for Privacy-Preserving Node Classification](https://mlsanity.com/paper/2005.11903/) (2020)
- [Federated Graph Neural Networks: Overview, Techniques and Challenges](https://mlsanity.com/paper/2202.07256/) (2022)
- [GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation](https://mlsanity.com/paper/2203.00949/) (2022)
- [Node-Level Differentially Private Graph Neural Networks](https://mlsanity.com/paper/2111.15521/) (2021)
- [Learning Differentially Private Recurrent Language Models](https://mlsanity.com/paper/1710.06963/) (2017)
- [Releasing Graph Neural Networks with Differential Privacy Guarantees](https://mlsanity.com/paper/2109.08907/) (2021)
- [Learn Locally, Correct Globally: A Distributed Algorithm for Training Graph Neural Networks](https://mlsanity.com/paper/2111.08202/) (2021)
- [FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks](https://mlsanity.com/paper/2104.07145/) (2021)

## Built on by (most cited first, 2 of 2)

- [Vertical Federated Learning for Effectiveness, Security, Applicability: A Survey](https://mlsanity.com/paper/2405.17495/) (2024)
- [On provable privacy vulnerabilities of graph representations](https://mlsanity.com/paper/2402.04033/) (2024)

## Abstract (arXiv)

The paradigm of vertical federated learning (VFL), where institutions collaboratively train machine learning models via combining each other's local feature or label information, has achieved great success in applications to financial risk management (FRM). The surging developments of graph representation learning (GRL) have opened up new opportunities for FRM applications under FL via efficiently utilizing the graph-structured data generated from underlying transaction networks. Meanwhile, transaction information is often considered highly sensitive. To prevent data leakage during training, it is critical to develop FL protocols with formal privacy guarantees. In this paper, we present an end-to-end GRL framework in the VFL setting called VESPER, which is built upon a general privatization scheme termed perturbed message passing (PMP) that allows the privatization of many popular graph neural architectures.Based on PMP, we discuss the strengths and weaknesses of specific design choices of concrete graph neural architectures and provide solutions and improvements for both dense and sparse graphs. Extensive empirical evaluations over both public datasets and an industry dataset demonstrate that VESPER is capable of training high-performance GNN models over both sparse and dense graphs under reasonable privacy budgets.