Wide and Deep Graph Neural Networks with Distributed Online Learning
arXiv:2006.06376
Abstract
Graph neural networks (GNNs) learn representations from network data with naturally distributed architectures, rendering them well-suited candidates for decentralized learning. Oftentimes, this decentralized graph support changes with time due to link failures or topology variations. These changes create a mismatch between the graphs on which GNNs were trained and the ones on which they are tested. Online learning can be used to retrain GNNs at testing time, overcoming this issue. However, most online algorithms are centralized and work on convex problems (which GNNs rarely lead to). This paper proposes the Wide and Deep GNN (WD-GNN), a novel architecture that can be easily updated with distributed online learning mechanisms. The WD-GNN comprises two components: the wide part is a bank of linear graph filters and the deep part is a GNN. At training time, the joint architecture learns a nonlinear representation from data. At testing time, the deep part (nonlinear) is left unchanged, while the wide part is retrained online, leading to a convex problem. We derive convergence guarantees for this online retraining procedure and further propose a decentralized alternative. Experiments on the robot swarm control for flocking corroborate theory and show potential of the proposed architecture for distributed online learning.
References in corpus (10)
- The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
- Geometric deep learning: going beyond Euclidean data
- Discrete Signal Processing on Graphs
- Simplifying Graph Convolutional Networks
- Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network
- Optimal Wireless Resource Allocation with Random Edge Graph Neural Networks
- Convolutional Neural Network Architectures for Signals Supported on Graphs
- Stability Properties of Graph Neural Networks
- Time-Varying Convex Optimization via Time-Varying Averaged Operators
- Controllability of Bandlimited Graph Processes Over Random Time Varying Graphs