Topological Neural Networks over the Air

Abstract

Topological neural networks (TNNs) are information processing architectures that model representations from data lying over topological spaces (e.g., simplicial or cell complexes) and allow for decentralized implementation through localized communications over different neighborhoods. Existing TNN architectures have not yet been considered in realistic communication scenarios, where channel effects typically introduce disturbances such as fading and noise. This paper aims to propose a novel TNN design, operating on regular cell complexes, that performs over-the-air computation, incorporating the wireless communication model into its architecture. Specifically, during training and inference, the proposed method considers channel impairments such as fading and noise in the topological convolutional filtering operation, which takes place over different signal orders and neighborhoods. Numerical results illustrate the architecture's robustness to channel impairments during testing and the superior performance with respect to existing architectures, which are either communication-agnostic or graph-based.

References in corpus (11)

• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Over the Air Deep Learning Based Radio Signal Classification
• Deep Joint Source-Channel Coding for Wireless Image Transmission
• Deep Learning-Based Communication Over the Air
• Topological Signal Processing over Simplicial Complexes
• Signal Processing on Higher-Order Networks: Livin' on the Edge ... and Beyond
• Detection Algorithms for Communication Systems Using Deep Learning
• Simplicial Convolutional Filters
• Signal Processing on Cell Complexes
• Topological Deep Learning: Going Beyond Graph Data
• Cell Attention Networks