CoNet-Rx: Collaborative Neural Networks for OFDM Receivers

2025-10-14

AI Summary

Existing deep learning–based OFDM receivers, largely adapted from computer vision architectures, suffer from high computational overhead and inference latency; lightweight variants often incur substantial performance degradation. Method: We propose CoNet, a collaborative neural network that employs multiple lightweight subnetworks (e.g., compact ResNet or CNN modules) operating in parallel to extract signal features, and introduces element-wise multiplication and other interaction operations to explicitly model channel correlations and interference patterns—enabling efficient feature fusion without increasing parameter count or computational complexity. Contribution/Results: Under identical model size constraints, CoNet achieves significantly lower bit error rate (BER) than baseline ResNet while reducing inference latency by over 30%. It thus delivers both high accuracy and low resource consumption, making it well-suited for edge wireless communication systems.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Deep learning (DL) based methods for orthogonal frequency division multiplexing (OFDM) radio receivers demonstrated higher signal detection performance compared to the traditional receivers. However, the existing DL-based models, usually adapted from computer vision, aren't well suited for wireless communications. These models require high computational resources and memory, and have significant inference delays, limiting their use in resource-constrained settings. Additionally, reducing network size to ease resource demands often leads to notable performance degradation. This paper introduces collaborative networks (CoNet), a novel neural network (NN) architecture designed for OFDM receivers. CoNet uses multiple small ResNet or CNN subnetworks to simultaneously process signal features from different perspectives like capturing channel correlations and interference patterns. These subnetworks fuse their outputs through interaction operations (e.g., element-wise multiplication), significantly enhancing detection performance. Simulation results show CoNet significantly outperforms traditional architectures like residual networks (ResNets) in bit error rate (BER) and reduces inference delay when both nets have the same size and the same computational complexity.

Problem

• Developing efficient neural networks for OFDM signal detection
• Reducing computational complexity and inference delay in receivers
• Maintaining performance while using smaller network architectures

Innovation

• Collaborative networks with multiple small subnetworks
• Simultaneously processes signal features from different perspectives
• Subnetworks fuse outputs through interaction operations