Decentralized Inference with Graph Neural Networks in Wireless Communication Systems
arXiv:2104.09027
Abstract
Graph neural network (GNN) is an efficient neural network model for graph data and is widely used in different fields, including wireless communications. Different from other neural network models, GNN can be implemented in a decentralized manner with information exchanges among neighbors, making it a potentially powerful tool for decentralized control in wireless communication systems. The main bottleneck, however, is wireless channel impairments that deteriorate the prediction robustness of GNN. To overcome this obstacle, we analyze and enhance the robustness of the decentralized GNN in different wireless communication systems in this paper. Specifically, using a GNN binary classifier as an example, we first develop a methodology to verify whether the predictions are robust. Then, we analyze the performance of the decentralized GNN binary classifier in both uncoded and coded wireless communication systems. To remedy imperfect wireless transmission and enhance the prediction robustness, we further propose novel retransmission mechanisms for the above two communication systems, respectively. Through simulations on the synthetic graph data, we validate our analysis, verify the effectiveness of the proposed retransmission mechanisms, and provide some insights for practical implementation.
arXiv commentThe paper was accpeted by TMC
References in corpus (15)
- Graph Neural Networks: A Review of Methods and Applications
- Learning to Optimize: Training Deep Neural Networks for Wireless Resource Management
- Provable defenses against adversarial examples via the convex outer adversarial polytope
- Machine Learning for Networking: Workflow, Advances and Opportunities
- Optimal Wireless Resource Allocation with Random Edge Graph Neural Networks
- Big Data Caching for Networking: Moving from Cloud to Edge
- An Iterative BP-CNN Architecture for Channel Decoding
- Spatial Deep Learning for Wireless Scheduling
- Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction
- Adversarial Attack on Graph Structured Data
- Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
- Certifiable Robustness to Graph Perturbations
- GraphSAC: Detecting anomalies in large-scale graphs
- Unifying local and non-local signal processing with graph CNNs
- Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Case