STFL: A Temporal-Spatial Federated Learning Framework for Graph Neural Networks

2021/11/12 by Guannan Lou, Yuze Liu, Lou, Guannan +5 · 3 citations
Computer Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data #Recommender Systems and Techniques #cs.AI #cs.LG

paper · pdf · doi:10.48550/arxiv.2111.06750

openalex publication_date 2021/11/12 · openalex created_date 2021/11/22 · arxiv created 2022/01/11 · arxiv updated 2022/01/12 · openalex updated_date 2026/07/28

Abstract

We present a spatial-temporal federated learning framework for graph neural networks, namely STFL. The framework explores the underlying correlation of the input spatial-temporal data and transform it to both node features and adjacency matrix. The federated learning setting in the framework ensures data privacy while achieving a good model generalization. Experiments results on the sleep stage dataset, ISRUC_S3, illustrate the effectiveness of STFL on graph prediction tasks.

Citations

• Adam: A Method for Stochastic Optimization
• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Advances and Open Problems in Federated Learning
• Cascade-BGNN: Toward Efficient Self-supervised Representation Learning on Large-scale Bipartite Graphs
• Federated Graph Learning -- A Position Paper
• Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modeling

Cited by

• A Comprehensive Data-centric Overview of Federated Graph Learning
• MetaSTH-Sleep: Towards Effective Few-Shot Sleep Stage Classification for Health Management with Spatial-Temporal Hypergraph Enhanced Meta-Learning
• FedHERO: A Federated Learning Approach for Node Classification Task on Heterophilic Graphs

Related

• An Adaptive Federated Relevance Framework for Spatial Temporal Graph Learning
• S2FGL: Spatial Spectral Federated Graph Learning
• Spatio-Temporal Graph Neural Networks: A Survey
• Federated Graph Neural Networks: Overview, Techniques and Challenges
• Federated Graph Learning -- A Position Paper