Related papers: Bit Allocation for Multi-Task Collaborative Intell…
We propose a novel segmentation-based explainable artificial intelligence (XAI) method for neural networks working on point cloud classification. As one building block of this method, we propose a novel point-shifting mechanism to introduce…
We consider a two-hop wireless network where a transmitter communicates with a receiver via $M$ relays with an amplify-and-forward (AF) protocol. Recent works have shown that sophisticated linear processing such as beamforming and…
The inference of Neural Networks is usually restricted by the resources (e.g., computing power, memory, bandwidth) on edge devices. In addition to improving the hardware design and deploying efficient models, it is possible to aggregate the…
The rapid growth of digital devices and IoT has intensified the demand for collaborative learning. Since these devices generate sensitive and high-dimensional data, centralized transmission is often impractical, while local learning suffers…
Network connectivity is one of the major design issues in the context of mobile sensor networks. Due to diverse communication patterns, some nodes lying in high-traffic zones may consume more energy and eventually die out resulting in…
For distributed estimations in a sensor network, the consistency and accuracy of an estimator are greatly affected by the unknown correlations between individual estimates. An inconsistent or too conservative estimate may degrade the…
We introduce a new and increasingly relevant setting for distributed optimization in machine learning, where the data defining the optimization are unevenly distributed over an extremely large number of nodes. The goal is to train a…
This paper investigates the adaptive subcarrier and bit allocation algorithm for OFDMA systems. To minimize overall transmitted power, we propose a novel adaptive subcarrier and bit allocation algorithm based on channel state information…
In a hierarchically-structured cloud/edge/device computing environment, workload allocation can greatly affect the overall system performance. This paper deals with AI-oriented medical workload generated in emergency rooms (ER) or intensive…
The Internet of Things (IoT) could enable the development of cloud multiple-input multiple-output (MIMO) systems where internet-enabled devices can work as distributed transmission/reception entities. We expect that spatial multiplexing…
Edge-cloud collaborative computing (ECCC) has emerged as a pivotal paradigm for addressing the computational demands of modern intelligent applications, integrating cloud resources with edge devices to enable efficient, low-latency…
5G D2D Communication promises improvements in energy and spectral efficiency, overall system capacity, and higher data rates. However, to achieve optimum results it is important to select wisely the Transmission mode of the D2D Device to…
Accurate segmenting nuclei instances is a crucial step in computer-aided image analysis to extract rich features for cellular estimation and following diagnosis as well as treatment. While it still remains challenging because the wide…
The rapid expansion of AI inference services in the cloud necessitates a robust scalability solution to manage dynamic workloads and maintain high performance. This study proposes a comprehensive scalability optimization framework for cloud…
Place recognition, an algorithm to recognize the re-visited places, plays the role of back-end optimization trigger in a full SLAM system. Many works equipped with deep learning tools, such as MLP, CNN, and transformer, have achieved great…
There has been much interest in deploying deep learning algorithms on low-powered devices, including smartphones, drones, and medical sensors. However, full-scale deep neural networks are often too resource-intensive in terms of energy and…
In this paper, we consider random access, wireless, multi-hop networks, with multi-packet reception capabilities, where multiple flows are forwarded to the gateways through node disjoint paths. We explore the issue of allocating flow on…
Most deep reinforcement learning algorithms are data inefficient in complex and rich environments, limiting their applicability to many scenarios. One direction for improving data efficiency is multitask learning with shared neural network…
Brain-computer interface (BCI) has garnered the significant attention for their potential in various applications, with event-related potential (ERP) performing a considerable role in BCI systems. This paper introduces a novel Distributed…
In this chapter, we will mainly focus on collaborative training across wireless devices. Training a ML model is equivalent to solving an optimization problem, and many distributed optimization algorithms have been developed over the last…