I. Introduction
The goal of next-generation communication systems is not only to increase throughput, lower latency, and improve reliabil-ity, but also to enhance autonomy by exploiting artificial neural network (ANN)-based communication algorithms [1], which allow for adaptation to varying channel conditions. Although such algorithms often enhance the communication performance of traditional approaches [2]–[4], the adaptation to changing conditions is based on a huge amount of data, required to perform supervised training of the ANN. This training data needs to be transmitted as pilot symbols, lowering the net throughput and information rate of the communication system. To solve this problem, an ANN-based channel equalizer is proposed in [5], which utilizes a generative adversarial net-work (GAN) to enable unsupervised training. For unsupervised training, no labels are required, therefore it can be performed without the overhead of transmitting pilot symbols. However, the GAN approach comes with increased computational complexity and instability introduced by an additional ANN serving as loss function.