Related papers: All you need is feedback: Communication with block…

Consider the Gaussian wiretap channel, where a transmitter wishes to send a confidential message to a legitimate receiver in the presence of an eavesdropper. It is well known that if the eavesdropper experiences less channel noise than the…

Attention-based transformers have become the standard architecture in many deep learning fields, primarily due to their ability to model long-range dependencies and handle variable-length input sequences. However, the attention mechanism…

Distributed learning algorithms, such as the ones employed in Federated Learning (FL), require communication compression to reduce the cost of client uploads. The compression methods used in practice are often biased, making error feedback…

Artificial intelligence (AI) provides an alternative way to design channel coding with affordable complexity. However, most existing studies can only learn codes for a given size and rate, typically defined by a fixed network architecture…

With the rapid growth in the volume of data sets, models, and devices in the domain of deep learning, there is increasing attention on large-scale distributed deep learning. In contrast to traditional distributed deep learning, the…

Task-oriented communication is a key enabler of emerging 6G systems, where the objective is to support decisions and actions rather than full message reconstruction. From an information-theoretic perspective, identification (ID) codes…

Transformer architectures have achieved remarkable success across language, vision, and multimodal tasks, and there is growing demand for them to address in-context compositional learning tasks. In these tasks, models solve the target…

Motivated by signal processing, we present a new class of channel codes, called signal codes, for continuous-alphabet channels. Signal codes are lattice codes whose encoding is done by convolving an integer information sequence with a fixed…

Deep neural networks have been applied in wireless communications system to intelligently adapt to dynamically changing channel conditions, while the users are still under the threat of the malicious attacks due to the broadcasting property…

The model of wiretap channel (WTC) is important as it constitutes the essence of physical layer security (PLS). Wiretap channel with noiseless feedback (WTC-NF) is especially interesting as it shows what can be done when a private feedback…

The design of reliable and efficient codes for channels with feedback remains a longstanding challenge in communication theory. While significant improvements have been achieved by leveraging deep learning techniques, neural codes often…

Consider communication over a channel whose probabilistic model is completely unknown vector-wise and is not assumed to be stationary. Communication over such channels is challenging because knowing the past does not indicate anything about…

One key requirement for fountain (rateless) coding schemes is to achieve a high intermediate symbol recovery rate. Recent coding schemes have incorporated the use of a feedback channel to improve intermediate performance of traditional…

We propose a new network architecture, Gated Attention Networks (GaAN), for learning on graphs. Unlike the traditional multi-head attention mechanism, which equally consumes all attention heads, GaAN uses a convolutional sub-network to…

As artificial intelligence systems spread to more diverse and larger tasks in many domains, the machine learning algorithms, and in particular the deep learning models and the databases required to train them are getting bigger themselves.…

Traditional convolutional neural networks (CNN) are stationary and feedforward. They neither change their parameters during evaluation nor use feedback from higher to lower layers. Real brains, however, do. So does our Deep Attention…

Deep neural networks excel at image classification, but their performance is far less robust to input perturbations than human perception. In this work we explore whether this shortcoming may be partly addressed by incorporating…

Transformers have achieved remarkable success across diverse domains, but their monolithic architecture presents challenges in interpretability, adaptability, and scalability. This paper introduces a novel modular Transformer architecture…

Whereas deep neural networks were first mostly used for classification tasks, they are rapidly expanding in the realm of structured output problems, where the observed target is composed of multiple random variables that have a rich joint…

This paper shows that deep neural network (DNN) can be used for efficient and distributed channel estimation, quantization, feedback, and downlink multiuser precoding for a frequency-division duplex massive multiple-input multiple-output…