Related papers: Simplicity is Key: An Unsupervised Pretraining App…

Recently self-supervised learning has emerged as an effective approach to improve the performance of automatic speech recognition (ASR). Under such a framework, the neural network is usually pre-trained with massive unlabeled data and then…

A unified view of sparse signal processing is presented in tutorial form by bringing together various fields. For each of these fields, various algorithms and techniques, which have been developed to leverage sparsity, are described…

This paper deals with distributed beamforming techniques for wireless networks with half-duplex amplify-and-forward relays. Existing schemes optimize the beamforming weights based on the assumption that channel state information (CSI) is…

This work introduces DeepCRF, a deep learning framework designed for channel state information-based radio frequency fingerprinting (CSI-RFF). The considered CSI-RFF is built on micro-CSI, a recently discovered radio-frequency (RF)…

We propose a simple and efficient algorithm for learning sparse invariant representations from unlabeled data with fast inference. When trained on short movies sequences, the learned features are selective to a range of orientations and…

Representation disentanglement is an important goal of representation learning that benefits various downstream tasks. To achieve this goal, many unsupervised learning representation disentanglement approaches have been developed. However,…

Many successful methods developed for medical image analysis that are based on machine learning use supervised learning approaches, which often require large datasets annotated by experts to achieve high accuracy. However, medical data…

This work gives a blind beamforming strategy for intelligent reflecting surface (IRS), aiming to boost the received signal-to-noise ratio (SNR) by coordinating phase shifts across reflective elements in the absence of channel information.…

The ultra-dense cloud radio access network (UD-CRAN), in which remote radio heads (RRHs) are densely deployed in the network, is considered. To reduce the channel estimation overhead, we focus on the design of robust transmit beamforming…

In recent years, the traditional feature engineering process for training machine learning models is being automated by the feature extraction layers integrated in deep learning architectures. In wireless networks, many studies were…

Motivated by the issue of inaccurate channel state information (CSI) at the base station (BS), which is commonly due to feedback/processing delays and compression problems, in this paper, we introduce a scalable idea of adopting artificial…

Many algorithms have been developed to solve the inverse problem of coded aperture snapshot spectral imaging (CASSI), i.e., recovering the 3D hyperspectral images (HSIs) from a 2D compressive measurement. In recent years, learning-based…

In future 6G cellular networks, a joint communication and sensing protocol will allow the network to perceive the environment, opening the door for many new applications atop a unified communication-perception infrastructure. However,…

Self-supervised speech representation learning (SSL) has shown to be effective in various downstream tasks, but SSL models are usually large and slow. Model compression techniques such as pruning aim to reduce the model size and computation…

We propose a new approach for power control in wireless networks using self-supervised learning. We partition a multi-layer perceptron that takes as input the channel matrix and outputs the power control decisions into a backbone and a…

In this work, we propose a novel joint client scheduling and resource block (RB) allocation policy to minimize the loss of accuracy in federated learning (FL) over wireless compared to a centralized training-based solution, under imperfect…

The task of parsing subcutaneous vessels in clinical images is often hindered by the high cost and limited availability of ground truth data, as well as the challenge of low contrast and noisy vessel appearances across different patients…

Unsupervised cross-lingual speech representation learning (XLSR) has recently shown promising results in speech recognition by leveraging vast amounts of unlabeled data across multiple languages. However, standard XLSR model suffers from…

Unsupervised pretraining, which learns a useful representation using a large amount of unlabeled data to facilitate the learning of downstream tasks, is a critical component of modern large-scale machine learning systems. Despite its…

In semi-supervised representation learning frameworks, when the number of labelled data is very scarce, the quality and representativeness of these samples become increasingly important. Existing literature on semi-supervised learning…