Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modeling
| Autor: | Yan Liu, Chuizheng Meng, Sirisha Rambhatla |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Edge device Computer science Computer Science - Artificial Intelligence Node (networking) Distributed computing Machine Learning (cs.LG) Temporal database Data sharing Traffic flow (computer networking) Artificial Intelligence (cs.AI) Data access Graph (abstract data type) Enhanced Data Rates for GSM Evolution |
| Zdroj: | KDD |
| Popis: | 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. To be published in the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 21) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|