Related papers: Get More for Less in Decentralized Learning System…

The recent many-fold increase in the size of deep neural networks makes efficient distributed training challenging. Many proposals exploit the compressibility of the gradients and propose lossy compression techniques to speed up the…

Deep neural networks have shown great success in low dose CT denoising. However, most of these deep neural networks have several hundred thousand trainable parameters. This, combined with the inherent non-linearity of the neural network,…

Federated Learning (FL) is an emerging paradigm through which decentralized devices can collaboratively train a common model. However, a serious concern is the leakage of privacy from exchanged gradient information between clients and the…

The diversity and quantity of data warehouses, gathering data from distributed devices such as mobile devices, can enhance the success and robustness of machine learning algorithms. Federated learning enables distributed participants to…

Deep neural networks (DNNs) have become core computation components within low latency Function as a Service (FaaS) prediction pipelines: including image recognition, object detection, natural language processing, speech synthesis, and…

Decentralized Federated Learning (DFL) trains models in a collaborative and privacy-preserving manner while removing model centralization risks and improving communication bottlenecks. However, DFL faces challenges in efficient…

Large amount of data is often required to train and deploy useful machine learning models in industry. Smaller enterprises do not have the luxury of accessing enough data for machine learning, For privacy sensitive fields such as banking,…

Deep neural networks (DNNs) have shown to provide superb performance in many real life applications, but their large computation cost and storage requirement have prevented them from being deployed to many edge and internet-of-things (IoT)…

Deep edge intelligence aims to deploy deep learning models that demand computationally expensive training in the edge network with limited computational power. Moreover, many deep edge intelligence applications require handling distributed…

Distributed learning, particularly variants of distributed stochastic gradient descent (DSGD), are widely employed to speed up training by leveraging computational resources of several workers. However, in practise, communication delay…

Deep learning (DL)-based channel state information (CSI) feedback has received significant research attention in recent years. However, previous research has overlooked the potential privacy disclosure problem caused by the transmission of…

Semantic communication has emerged as a promising approach for improving efficient transmission in the next generation of wireless networks. Inspired by the success of semantic communication in different areas, we aim to provide a new…

Learning predictive models from observations using deep neural networks (DNNs) is a promising new approach to many real-world planning and control problems. However, common DNNs are too unstructured for effective planning, and current…

With joint learning of sampling and recovery, the deep learning-based compressive sensing (DCS) has shown significant improvement in performance and running time reduction. Its reconstructed image, however, losses high-frequency content…

Large-scale supervised classification algorithms, especially those based on deep convolutional neural networks (DCNNs), require vast amounts of training data to achieve state-of-the-art performance. Decreasing this data requirement would…

The data-driven sparse methods such as synthesis dictionary learning (e.g., K-SVD) and sparsifying transform learning have been proven effective in image denoising. However, they are intrinsically single-scale which can lead to suboptimal…

Federated learning (FL) enables collaborative model training across distributed clients while preserving data locality. Although FedAvg pioneered synchronous rounds for global model averaging, slower devices can delay collective progress.…

Compressed communication, in the form of sparsification or quantization of stochastic gradients, is employed to reduce communication costs in distributed data-parallel training of deep neural networks. However, there exists a discrepancy…

Image denoising aims to restore a clean image from an observed noisy image. The model-based image denoising approaches can achieve good generalization ability over different noise levels and are with high interpretability. Learning-based…

To reduce uploading bandwidth and address privacy concerns, deep learning at the network edge has been an emerging topic. Typically, edge devices collaboratively train a shared model using real-time generated data through the Parameter…