Learning During Detection: Continual Learning for Neural OFDM Receivers via DMRS

2026-02-23

AI Summary

This work addresses the vulnerability of neural OFDM receivers to distribution shifts in rapidly time-varying channels, which typically necessitates frequent retraining and incurs overhead with conventional approaches. The authors propose a zero-overhead online continual learning framework that, for the first time, leverages standard DMRS signals to simultaneously perform soft-bit detection and model adaptation—eliminating the need for dedicated training periods or service interruption. By introducing three pilot strategies (random, hybrid, and augmented) and two low-complexity receiver architectures (parallel and forward-reuse), the framework effectively tracks channel dynamics under both slow and fast fading conditions, mitigates catastrophic forgetting, and achieves these gains without any additional resource overhead.

Technology Category

• Machine Learning: Life-Long and Continual Learning
• Search and Optimization: Learning to Search
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Deep neural networks (DNNs) have been increasingly explored for receiver design because they can handle complex environments without relying on explicit channel models. Nevertheless, because communication channels change rapidly, their distributions can shift over time, often making periodic retraining necessary. This paper proposes a zero-overhead online and continual learning framework for orthogonal frequency-division multiplexing (OFDM) neural receivers that directly detect the soft bits of received signals. Unlike conventional fine-tuning methods that rely on dedicated training intervals or full resource grids, our approach leverages existing demodulation reference signals (DMRS) to simultaneously enable signal demodulation and model adaptation. We introduce three pilot designs: fully randomized, hybrid, and additional pilots that flexibly support joint demodulation and learning. To accommodate these pilot designs, we develop two receiver architectures: (i) a parallel design that separates inference and fine-tuning for uninterrupted operation, and (ii) a forward-pass reusing design that reduces computational complexity. Simulation results show that the proposed method effectively tracks both slow and fast channel distribution variations without additional overhead, service interruption, or catastrophic performance degradation under distribution shift.

Problem

• continual learning
• OFDM receivers
• distribution shift
• channel variation
• online learning

Innovation

• continual learning
• neural receiver
• DMRS
• OFDM
• zero-overhead adaptation