Related papers: MTL-Split: Multi-Task Learning for Edge Devices us…

Deep neural networks (DNNs) have recently achieved impressive success across a wide range of real-world vision and language processing tasks, spanning from image classification to many other downstream vision tasks, such as object…

Recent studies have shown the latency and energy consumption of deep neural networks can be significantly improved by splitting the network between the mobile device and cloud. This paper introduces a new deep learning architecture, called…

Network slicing in 5G/6G Non-Terrestrial Network (NTN) is confronted with mobility and traffic variability. An artificial intelligence (AI)-based digital twin (DT) architecture with deep reinforcement learning (DRL) using Deep deterministic…

Deep learning has shown impressive performance in semantic segmentation, but it is still unaffordable for resource-constrained mobile devices. While offloading computation tasks is promising, the high traffic demands overwhelm the limited…

Convolutional Neural Network (CNN) or Long short-term memory (LSTM) based models with the input of spectrogram or waveforms are commonly used for deep learning based audio source separation. In this paper, we propose a Sliced…

The quantum convolutional neural network (QCNN) is a promising quantum machine learning (QML) model that is expected to achieve quantum advantages in classically intractable problems. However, the QCNN requires a large number of…

This paper proposes a neural architecture search (NAS) method for split computing. Split computing is an emerging machine-learning inference technique that addresses the privacy and latency challenges of deploying deep learning in IoT…

When pre-trained models become rapidly larger, the cost of fine-tuning on downstream tasks steadily increases, too. To economically fine-tune these models, parameter-efficient transfer learning (PETL) is proposed, which only tunes a tiny…

Intelligent transportation systems (ITSs) will be a major component of tomorrow's smart cities. However, realizing the true potential of ITSs requires ultra-low latency and reliable data analytics solutions that can combine, in real-time, a…

Edge computing has emerged as a popular paradigm for supporting mobile and IoT applications with low latency or high bandwidth needs. The attractiveness of edge computing has been further enhanced due to the recent availability of…

Deep Neural Networks (DNNs) are becoming an important tool in modern computing applications. Accelerating their training is a major challenge and techniques range from distributed algorithms to low-level circuit design. In this survey, we…

In this paper, a proactive dynamic spectrum sharing scheme between 4G and 5G systems is proposed. In particular, a controller decides on the resource split between NR and LTE every subframe while accounting for future network states such as…

Device-edge collaboration on deep neural network (DNN) inference is a promising approach to efficiently utilizing network resources for supporting artificial intelligence of things (AIoT) applications. In this paper, we propose a novel…

Despite the recent progress in deep learning, most approaches still go for a silo-like solution, focusing on learning each task in isolation: training a separate neural network for each individual task. Many real-world problems, however,…

Multi-Task Learning (MTL) aims at boosting the overall performance of each individual task by leveraging useful information contained in multiple related tasks. It has shown great success in natural language processing (NLP). Currently, a…

5G and beyond is expected to enable various emerging use cases with diverse performance requirements from vertical industries. To serve these use cases cost-effectively, network slicing plays a key role in dynamically creating virtual…

In this paper, we provide a series of multi-tasking benchmarks for simultaneously detecting spoofing at the segmental and utterance levels in the PartialSpoof database. First, we propose the SELCNN network, which inserts…

Edge computing has emerged as a prospective paradigm to meet ever-increasing computation demands in Mobile Target Tracking Wireless Sensor Networks (MTT-WSN). This paradigm can offload time-sensitive tasks to sink nodes to improve computing…

With the increased penetration and proliferation of Internet of Things (IoT) devices, there is a growing trend towards distributing the power of deep learning (DL) across edge devices rather than centralizing it in the cloud. This…

The wireless network is undergoing a trend from "onnection of things" to "connection of intelligence". With data spread over the communication networks and computing capability enhanced on the devices, distributed learning becomes a hot…