Single-Step Online Adaptation of Modular Bayesian Deep Receivers with Streaming Data

Deep neural network-based receivers offer a powerful alternative to classical model-based designs for wireless communication, especially in complex and nonlinear propagation environments. However, their adoption is challenged by the rapid variability of wireless channels, which makes pre-trained static DNN-based receivers ineffective, and by the latency and computational burden of online SGD-based continual learning. In this work, we propose an online learning framework that enables rapid low-complexity adaptation of DNN-based receivers. Our approach is based on two main tenets. First, we cast online learning as Bayesian tracking in parameter space, enabling a single-step adaptation which deviates from multi-epoch SGD. Second, we focus on modular DNN architectures enabling parallel and localized Bayesian updates, where each module maintains its own variational posterior. Simulations with practical dynamic communication channels demonstrate state-of-the-art error rate performance.