Channel Agnostic End-to-End Learning Based Communication Systems with Conditional GAN

By Hao Ye, Geoffrey Y. Li, Biing-Hwang Fred Juang, Kathiravetpillai Sivanesan. 2018

234 citations recorded by the source corpus.

In this article, we use deep neural networks (DNNs) to develop an end-to-end wireless communication system, in which DNNs are employed for all signal-related functionalities, including encoding, decoding, modulation, and equalization. However, accurate instantaneous channel transfer function, i.e., the channel state information (CSI), is necessary to compute the gradient of the DNN representing. In many communication systems, the channel transfer function is hard to obtain in advance and varies with time and location. In this article, this constraint is released by developing a channel agnostic end-to-end system that does not rely on any prior information about the channel. We use a conditional generative adversarial net (GAN) to represent the channel effects, where the encoded signal of the transmitter will serve as the conditioning information. In addition, in order to obtain accurate channel state information for signal detection at the receiver, the received signal corresponding to the pilot data is added as a part of the conditioning information. From the simulation results, the proposed method is effective on additive white Gaussian noise (AWGN) and Rayleigh fading channels, which opens a new door for building data-driven communication systems.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Molecular Biology

Citations in the corpus

Wireless Network Intelligence at the Edge (2018, methodology): “Toward this vision, at the physical layer, an E2E communication framework was studied under unknown channels using an autoencoder (AE) [19], [20], recurrent NN (RNN) [21], and generative adversarial network (GAN) [22].”
Wireless Image Transmission Using Deep Source Channel Coding With Attention Modules (2020, background): “Other approaches adopted to support effective wireless communications have resorted to reinforcement learning and generative adversarial networks [26], [27].”
Deep Learning-Based End-to-End Wireless Communication Systems With Conditional GANs as Unknown Channels (2019, background): “Part of the work has been published in [22].”
Deep Learning in Mobile and Wireless Networking: A Survey (2018, background): “[509] Channel agnostic end-to-end learning based communication system Conditional GAN”
Wireless Networks Design in the Era of Deep Learning: Model-Based, AI-Based, or Both? (2019, background): “are used in [168]–[170], by exploiting a surrogate channel for training purposes.”
Quantum Machine Learning for 6G Communication Networks: State-of-the-Art and Vision for the Future (2019, background): “For example, a DNN-based end-to-end learning system is proposed in [18], where a channel agnostic learning based system is proposed for learning the channel output through a conditional Generative Adversarial Net (GAN).”
Deep Learning in Physical Layer Communications (2018, methodology): “condItIonAl gAn-bAsed end-to-end systems In order to solve the missing gradient problem and lower the demands for the large amount of training data, a generative approach based on conditional GAN has been proposed in [4].”
A Very Brief Introduction to Machine Learning With Applications to Communication Systems (2018, background): “A natural idea is that of using generative models to learn how to generate samples from a given channel [71], [72].”
Model-Driven Deep Learning for Physical Layer Communications (2018, methodology): “In [11], the purely data-driven DL method has been used in transceiver optimization without using accurate CSI.”
Machine Learning in the Air (2019, methodology): “In [41], the authors propose to use the learned GAN as the channel layer between the encoder and decoder NNs of an end-to-end communication system.”
6G Networks: Beyond Shannon Towards Semantic and Goal-Oriented Communications (2020, background): “Examples of application of machine learning tools to the physical layer of a communication system have been already studied, under unknown channels, using an autoencoder (AE) [58], [59], a recurrent neural network (RNN) [60], and a generative adversarial network (GAN) [61].”