# FedGraph: Federated Graph Learning with Intelligent Sampling

arXiv: https://arxiv.org/abs/2111.01370 · HTML: https://mlsanity.com/paper/2111.01370/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 49 references that are in the map.
- First posted on arXiv 2 Nov 2021.

## Builds on (most cited first, 22 of 22)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [Simple and Deep Graph Convolutional Networks](https://mlsanity.com/paper/2007.02133/) (2020)
- [DropEdge: Towards Deep Graph Convolutional Networks on Node Classification](https://mlsanity.com/paper/1907.10903/) (2019)
- [FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling](https://mlsanity.com/paper/1801.10247/) (2018)
- [Federated Optimization: Distributed Machine Learning for On-Device Intelligence](https://mlsanity.com/paper/1610.02527/) (2016)
- [Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks](https://mlsanity.com/paper/1905.07953/) (2019)
- [Adaptive Sampling Towards Fast Graph Representation Learning](https://mlsanity.com/paper/1809.05343/) (2018)
- [Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks](https://mlsanity.com/paper/1911.07323/) (2019)
- [GRAM: Graph-based Attention Model for Healthcare Representation Learning](https://mlsanity.com/paper/1611.07012/) (2016)
- [Graph Convolutional Encoders for Syntax-aware Neural Machine Translation](https://mlsanity.com/paper/1704.04675/) (2017)
- [ASFGNN: Automated Separated-Federated Graph Neural Network](https://mlsanity.com/paper/2011.03248/) (2020)
- [Towards Federated Graph Learning for Collaborative Financial Crimes Detection](https://mlsanity.com/paper/1909.12946/) (2019)
- [Federated Dynamic GNN with Secure Aggregation](https://mlsanity.com/paper/2009.07351/) (2020)

## Built on by (most cited first, 30 of 34)

- [Trustworthy Graph Neural Networks: Aspects, Methods and Trends](https://mlsanity.com/paper/2205.07424/) (2022)
- [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)
- [Inductive Graph Unlearning](https://mlsanity.com/paper/2304.03093/) (2023)
- [Federated Graph Machine Learning: A Survey of Concepts, Techniques, and Applications](https://mlsanity.com/paper/2207.11812/) (2022)
- [Deep Efficient Private Neighbor Generation for Subgraph Federated Learning](https://mlsanity.com/paper/2401.04336/) (2024)
- [SecGNN: Privacy-Preserving Graph Neural Network Training and Inference as a Cloud Service](https://mlsanity.com/paper/2202.07835/) (2022)
- [Privacy-Preserving Graph Machine Learning from Data to Computation: A Survey](https://mlsanity.com/paper/2307.04338/) (2023)
- [A Comprehensive Data-centric Overview of Federated Graph Learning](https://mlsanity.com/paper/2507.16541/) (2025)
- [Lumos: Heterogeneity-aware Federated Graph Learning over Decentralized Devices](https://mlsanity.com/paper/2303.00492/) (2023)
- [Subgraph Federated Learning via Spectral Methods](https://mlsanity.com/paper/2510.25657/) (2025)
- [Edge-cloud Collaborative Learning with Federated and Centralized Features](https://mlsanity.com/paper/2304.05871/) (2023)
- [FedGT: Federated Node Classification with Scalable Graph Transformer](https://mlsanity.com/paper/2401.15203/) (2024)
- [HiFGL: A Hierarchical Framework for Cross-silo Cross-device Federated Graph Learning](https://mlsanity.com/paper/2406.10616/) (2024)
- [GLASU: A Communication-Efficient Algorithm for Federated Learning with Vertically Distributed Graph Data](https://mlsanity.com/paper/2303.09531/) (2023)
- [Decoupled Subgraph Federated Learning](https://mlsanity.com/paper/2402.19163/) (2024)
- [Efficient Model Compression for Hierarchical Federated Learning](https://mlsanity.com/paper/2405.17522/) (2024)
- [Edge Graph Intelligence: Reciprocally Empowering Edge Networks with Graph Intelligence](https://mlsanity.com/paper/2407.15320/) (2024)
- [Federated Learning Based Distributed Localization of False Data Injection Attacks on Smart Grids](https://mlsanity.com/paper/2306.10420/) (2023)
- [DGC: Training Dynamic Graphs with Spatio-Temporal Non-Uniformity using Graph Partitioning by Chunks](https://mlsanity.com/paper/2309.03523/) (2023)
- [Against Multifaceted Graph Heterogeneity via Asymmetric Federated Prompt Learning](https://mlsanity.com/paper/2411.02003/) (2024)
- [FedGrAINS: Personalized SubGraph Federated Learning with Adaptive Neighbor Sampling](https://mlsanity.com/paper/2501.12592/) (2025)
- [Federated Fine-Tuning of Sparsely-Activated Large Language Models on Resource-Constrained Devices](https://mlsanity.com/paper/2508.19078/) (2025)
- [Federated Graph Representation Learning using Self-Supervision](https://mlsanity.com/paper/2210.15120/) (2022)
- [SpreadFGL: Edge-Client Collaborative Federated Graph Learning with Adaptive Neighbor Generation](https://mlsanity.com/paper/2407.11085/) (2024)
- [Federated Hypergraph Learning with Local Differential Privacy: Toward Privacy-Aware Hypergraph Structure Completion](https://mlsanity.com/paper/2408.05160/) (2024)
- [Query-Efficient Adversarial Attack Against Vertical Federated Graph Learning](https://mlsanity.com/paper/2411.02809/) (2024)
- [DM4Steal: Diffusion Model For Link Stealing Attack On Graph Neural Networks](https://mlsanity.com/paper/2411.03364/) (2024)
- [Attributed Graph Clustering in Collaborative Settings](https://mlsanity.com/paper/2411.12329/) (2024)
- [Intelligent Sampling of Extreme-Scale Turbulence Datasets for Accurate and Efficient Spatiotemporal Model Training](https://mlsanity.com/paper/2508.03872/) (2025)

## Abstract (arXiv)

Federated learning has attracted much research attention due to its privacy protection in distributed machine learning. However, existing work of federated learning mainly focuses on Convolutional Neural Network (CNN), which cannot efficiently handle graph data that are popular in many applications. Graph Convolutional Network (GCN) has been proposed as one of the most promising techniques for graph learning, but its federated setting has been seldom explored. In this paper, we propose FedGraph for federated graph learning among multiple computing clients, each of which holds a subgraph. FedGraph provides strong graph learning capability across clients by addressing two unique challenges. First, traditional GCN training needs feature data sharing among clients, leading to risk of privacy leakage. FedGraph solves this issue using a novel cross-client convolution operation. The second challenge is high GCN training overhead incurred by large graph size. We propose an intelligent graph sampling algorithm based on deep reinforcement learning, which can automatically converge to the optimal sampling policies that balance training speed and accuracy. We implement FedGraph based on PyTorch and deploy it on a testbed for performance evaluation. The experimental results of four popular datasets demonstrate that FedGraph significantly outperforms existing work by enabling faster convergence to higher accuracy.