Asynchronous Online Adaptation via Modular Drift Detection for Deep Receivers

TL;DR

This work addresses the challenge of adapting deep receivers to time-varying wireless channels without incurring the high cost of continuous retraining. By framing adaptation as a concept-drift problem, it introduces soft-output drift detectors and extends this to modular drift detection for hybrid model-based/data-driven receivers, enabling asynchronous and module-wise retraining. The proposed detectors (posterior-based and Hotelling-based) leverage soft outputs to trigger retraining only when necessary, and modular drift detection further reduces complexity by confining updates to affected sub-modules. Across SISO and MIMO scenarios, including COST2100 channels, the approach achieves substantial reductions in retraining effort (often by factors of 10–40) with minimal BER degradation, demonstrating practical viability for resource-constrained wireless devices.

Abstract

Deep learning is envisioned to facilitate the operation of wireless receivers, with emerging architectures integrating deep neural networks (DNNs) with traditional modular receiver processing. While deep receivers were shown to operate reliably in complex settings for which they were trained, the dynamic nature of wireless communications gives rise to the need to repeatedly adapt deep receivers to channel variations. However, frequent re-training is costly and ineffective, while in practice, not every channel variation necessitates adaptation of the entire DNN. In this paper, we study concept drift detection for identifying when does a deep receiver no longer match the channel, enabling asynchronous adaptation, i.e., re-training only when necessary. We identify existing drift detection schemes from the machine learning literature that can be adapted for deep receivers in dynamic channels, and propose a novel soft-output detection mechanism tailored to the communication domain. Moreover, for deep receivers that preserve conventional modular receiver processing, we design modular drift detection mechanisms, that simultaneously identify when and which sub-module to re-train. The provided numerical studies show that even in a rapidly time-varying scenarios, asynchronous adaptation via modular drift detection dramatically reduces the number of trained parameters and re-training times, with little compromise on performance.

Figures (13)

• Figure 1: Schematic illustration of $(a)$ synchronous online learning compared to $(b)$ asynchronous online learning.
• Figure 2: Channel variation profiles.
• Figure 3: Aggregated ber versus block. SISO COST2100 Channel. Markers indicate re-training blocks.
• Figure 4: Average ber versus SNR. SISO COST2100 Channel.
• Figure 5: Aggregated ber versus block. MIMO Single-User Variations Channel. Markers indicate re-training blocks.

Theorems & Definitions (2)

• Proposition 1
• Corollary 1