GLASU: A Communication-Efficient Algorithm for Federated Learning with Vertically Distributed Graph Data
Not on the map. Why?
Abstract (arXiv)
Vertical federated learning (VFL) is a distributed learning paradigm, where computing clients collectively train a model based on the partial features of the same set of samples they possess. Current research on VFL focuses on the case when samples are independent, but it rarely addresses an emerging scenario when samples are interrelated through a graph. For graph-structured data, graph neural networks (GNNs) are competitive machine learning models, but a naive implementation in the VFL setting causes a significant communication overhead. Moreover, the analysis of the training is faced with a challenge caused by the biased stochastic gradients. In this paper, we propose a model splitting method that splits a backbone GNN across the clients and the server and a communication-efficient algorithm, GLASU, to train such a model. GLASU adopts lazy aggregation and stale updates to skip aggregation when evaluating the model and skip feature exchanges during training, greatly reducing communication. We offer a theoretical analysis and conduct extensive numerical experiments on real-world datasets, showing that the proposed algorithm effectively trains a GNN model, whose performance matches that of the backbone GNN when trained in a centralized manner.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 28 of its 39 references that are in the map. First posted on arXiv 16 Mar 2023.
Builds on
28 of 39 references.
References · 28
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2017Graph Attention Networkscited by 8,854
- 2017Inductive Representation Learning on Large Graphscited by 6,284
- 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
- 2020Simple and Deep Graph Convolutional Networkscited by 857
- 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 583
- 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
- 2015An Introduction to Matrix Concentration Inequalitiescited by 391
- 2020SplitFed: When Federated Learning Meets Split Learningcited by 308
- 2017Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryptioncited by 174
- 2021Subgraph Federated Learning with Missing Neighbor Generationcited by 132
- 2021Federated Graph Classification over Non-IID Graphscited by 113
16 more
- 2020VAFL: a Method of Vertical Asynchronous Federated Learningcited by 87
- 2019Peer-to-peer Federated Learning on Graphscited by 85
- 2021Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modelingcited by 69
- 2020GraphFL: A Federated Learning Framework for Semi-Supervised Node Classification on Graphscited by 64
- 2020Vertically Federated Graph Neural Network for Privacy-Preserving Node Classificationcited by 61
- 2019Parallel Distributed Logistic Regression for Vertical Federated Learning without Third-Party Coordinatorcited by 51
- 2021Cluster-driven Graph Federated Learning over Multiple Domainscited by 43
- 2019A Quasi-Newton Method Based Vertical Federated Learning Framework for Logistic Regressioncited by 37
- 2020ASFGNN: Automated Separated-Federated Graph Neural Networkcited by 36
- 2021PyVertical: A Vertical Federated Learning Framework for Multi-headed SplitNNcited by 35
- 2021FedGL: Federated Graph Learning Framework with Global Self-Supervisioncited by 34
- 2021Federated Graph Learning -- A Position Papercited by 34
- 2021FedGraph: Federated Graph Learning with Intelligent Samplingcited by 34
- 2021FedV: Privacy-Preserving Federated Learning over Vertically Partitioned Datacited by 31
- 2021A Vertical Federated Learning Framework for Graph Convolutional Networkcited by 20
- 2021A Graph Federated Architecture with Privacy Preserving Learningcited by 10
Built on by
Citing papers per year: 2024: 2; 2025: 1.
3 papers.