Hybrid Neural/Traditional OFDM Receiver with Learnable Decider

2025-09-22

AI Summary

Deep learning-based OFDM receivers suffer from poor generalization and inadequate channel tracking under unknown or rapidly time-varying channels. To address this, we propose an adaptive hybrid receiver architecture that dynamically switches between conventional and neural processing paths. Its core innovation is a trainable discriminative network that selects the optimal reception path per OFDM symbol block based on channel features—such as statistical metrics derived from pilot responses—and explicitly models the performance gap between conventional and deep learning receivers via pilot-aided supervision. Robustness is further enhanced by augmenting training with anomalous channel samples. Experimental results demonstrate that the proposed method achieves significantly lower bit error rates than either standalone conventional or deep learning receivers across diverse channel conditions—including static, Doppler-spread, and bursty fading scenarios—while maintaining both high accuracy and strong generalization capability.

Technology Category

• Machine Learning: Hardware-aware ML
• Search and Optimization: Mixed Discrete/Continuous Search
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Deep learning (DL) methods have emerged as promising solutions for enhancing receiver performance in wireless orthogonal frequency-division multiplexing (OFDM) systems, offering significant improvements over traditional estimation and detection techniques. However, DL-based receivers often face challenges such as poor generalization to unseen channel conditions and difficulty in effectively tracking rapid channel fluctuations. To address these limitations, this paper proposes a hybrid receiver architecture that integrates the strengths of both traditional and neural receivers. The core innovation is a discriminator neural network trained to dynamically select the optimal receiver whether it is the traditional or DL-based receiver according on the received OFDM block characteristics. This discriminator is trained using labeled pilot signals that encode the comparative performance of both receivers. By including anomalous channel scenarios in training, the proposed hybrid receiver achieves robust performance, effectively overcoming the generalization issues inherent in standalone DL approaches.

Problem

• Improving OFDM receiver performance by combining traditional and neural approaches
• Addressing poor generalization of DL receivers to unseen channel conditions
• Solving difficulty in tracking rapid channel fluctuations with neural networks

Innovation

• Hybrid receiver combining traditional and neural approaches
• Discriminator neural network dynamically selects optimal receiver
• Training with anomalous channels ensures robust generalization