Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modeling
Authors:
Open Access
- 14 August 2021
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1202-1211
Abstract
Vast amount of data generated from networks of sensors, wearables, and the Internet of Things (IoT) devices underscores the need for advanced modeling techniques that leverage the spatio-temporal structure of decentralized data due to the need for edge computation and licensing (data access) issues. While federated learning (FL) has emerged as a framework for model training without requiring direct data sharing and exchange, effectively modeling the complex spatio-temporal dependencies to improve forecasting capabilities still remains an open problem. On the other hand, state-of-the-art spatio-temporal forecasting models assume unfettered access to the data, neglecting constraints on data sharing. To bridge this gap, we propose a federated spatio-temporal model -- Cross-Node Federated Graph Neural Network (CNFGNN) -- which explicitly encodes the underlying graph structure using graph neural network (GNN)-based architecture under the constraint of cross-node federated learning, which requires that data in a network of nodes is generated locally on each node and remains decentralized. CNFGNN operates by disentangling the temporal dynamics modeling on devices and spatial dynamics on the server, utilizing alternating optimization to reduce the communication cost, facilitating computations on the edge devices. Experiments on the traffic flow forecasting task show that CNFGNN achieves the best forecasting performance in both transductive and inductive learning settings with no extra computation cost on edge devices, while incurring modest communication cost.Keywords
Funding Information
- NSF Research Grant IIS (IIS-1254206)
- WeWork
- NSF Research Grant CCF (CCF-1837131)
This publication has 7 references indexed in Scilit:
- Graph-Temporal LSTM Networks for Skeleton-Based Action Recognition2020
- SGNN: A Graph Neural Network Based Federated Learning Approach by Hiding Structure2019
- Graph Convolutional Neural Networks for Web-Scale Recommender Systems2018
- Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting2018
- Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action RecognitionProceedings of the AAAI Conference on Artificial Intelligence, 2018
- Non-convex Optimization for Machine LearningFoundations and Trends in Machine Learning, 2017
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation2014