Related papers: Generalized Sparse and Low-Rank Optimization for U…

The acceleration of pruned Deep Neural Networks (DNNs) on edge devices such as Microcontrollers (MCUs) is a challenging task, given the tight area- and power-constraints of these devices. In this work, we propose a three-fold contribution…

6G networks are expected to integrate low Earth orbit satellites to ensure global connectivity by extending coverage to underserved and remote regions. However, the deployment of dense mega-constellations introduces severe interference…

Industry-led initiatives such as the Next G Alliance (NGA) are currently considering how to dimension the spectrum required to support new classes of services envisioned beyond 5G. In particular, support for URLLC brings the challenge of…

The development and implementation of Internet of Things (IoT) devices have been accelerated dramatically in recent years. As a result, a super-network is required to handle the massive volumes of data collected and transmitted to these…

Networking data analytics is increasingly used for enhanced network visibility and controllability. We draw the similarities between the Software Defined Networking (SDN) architecture and the MapReduce programming model. Inspired by the…

Recurrent Neural Networks (RNN) are widely used to solve a variety of problems and as the quantity of data and the amount of available compute have increased, so have model sizes. The number of parameters in recent state-of-the-art networks…

The most promising approach to enhance network capacity for the next generation of wireless cellular networks (5G) is densification, which benefits from the extensive spatial reuse of the spectrum and the reduced distance between…

Deep neural network (DNN) inference is increasingly being executed on mobile and embedded platforms due to low latency and better privacy. However, efficient deployment on these platforms is challenging due to the intensive computation and…

Medical image segmentation using deep neural networks has been highly successful. However, the effectiveness of these networks is often limited by inadequate dense prediction and inability to extract robust features. To achieve refined…

Traditional communication networks consist of large sets of vendor-specific manually configurable devices which are hardwired with specific control logic or algorithms. The resulting networks comprise distributed control plane architectures…

Small cell enchantment is emerging as the key technique for wireless network evolution. One challenging problem for small cell enhancement is how to achieve high data rate with as-low-as-possible control and computation overheads. As a…

Ultra reliable low latency communications (URLLC) is a new service class introduced in 5G which is characterized by strict reliability $(1-10^{-5})$ and low latency requirements (1 ms). To meet these requisites, several strategies like…

The demand for efficient processing of deep neural networks (DNNs) on embedded devices is a significant challenge limiting their deployment. Exploiting sparsity in the network's feature maps is one of the ways to reduce its inference…

In fifth generation (5G) and beyond Internet of Things (IoT), it becomes increasingly important to serve a massive number of IoT devices outside the coverage of terrestrial cellular networks. Due to their own limitations, unmanned aerial…

Computer networks have become a critical infrastructure. In fact, networks should not only meet strict requirements in terms of correctness, availability, and performance, but they should also be very flexible and support fast updates,…

Deep Neural Networks (DNNs) are universal function approximators providing state-of- the-art solutions on wide range of applications. Common perceptual tasks such as speech recognition, image classification, and object tracking are now…

This paper investigates deep learning enabled beamforming design for ultra-dense wireless networks by integrating prior knowledge and graph neural network (GNN), named model-based GNN. A energy efficiency (EE) maximization problem is…

Due to their great performance and scalability properties neural networks have become ubiquitous building blocks of many applications. With the rise of mobile and IoT, these models now are also being increasingly applied in distributed…

We present a novel network pruning algorithm called Dynamic Sparse Training that can jointly find the optimal network parameters and sparse network structure in a unified optimization process with trainable pruning thresholds. These…

The lack of mathematical tractability of Deep Neural Networks (DNNs) has hindered progress towards having a unified convergence analysis of training algorithms, in the general setting. We propose a unified optimization framework for…