Related papers: Online Algorithms for Hierarchical Inference in De…

Stable Diffusion Models (SDMs) have shown remarkable proficiency in image synthesis. However, their broad application is impeded by their large model sizes and intensive computational requirements, which typically require expensive cloud…

Implanted devices providing real-time neural activity classification and control are increasingly used to treat neurological disorders, such as epilepsy and Parkinson's disease. Classification performance is critical to identifying brain…

Large language models (LLMs) are becoming increasingly capable at small parameter scales. At the same time, conventional cloud-centric deployment introduces challenges around data privacy, latency, and cost that are acute in operational…

Hyperspectral image (HSI) classification presents unique challenges due to its high spectral dimensionality and limited labeled data. Traditional deep learning models often suffer from overfitting and high computational costs.…

Owing to the large volume of sensed data from the enormous number of IoT devices in operation today, centralized machine learning algorithms operating on such data incur an unbearable training time, and thus cannot satisfy the requirements…

Privacy-preserving machine learning (PPML) has become increasingly important in applications where sensitive data must remain confidential. Homomorphic Encryption (HE) enables computation directly on encrypted data, allowing neural network…

Edge machine learning can deliver low-latency and private artificial intelligent (AI) services for mobile devices by leveraging computation and storage resources at the network edge. This paper presents an energy-efficient edge processing…

With the proliferation of edge computing, efficient AI inference on edge devices has become essential for intelligent applications such as autonomous vehicles and VR/AR. In this context, we address the problem of efficient remote object…

The convergence of artificial intelligence and edge computing has spurred growing interest in enabling intelligent services directly on resource-constrained devices. While traditional deep learning models require significant computational…

A significant increase in the number of interconnected devices and data communication through wireless networks has given rise to various threats, risks and security concerns. Internet of Things (IoT) applications is deployed in almost…

We consider a multi-user multi-server mobile edge computing (MEC) system, in which users arrive on a network randomly over time and generate computation tasks, which will be computed either locally on their own computing devices or be…

Since real-world objects and their interactions are often multi-modal and multi-typed, heterogeneous networks have been widely used as a more powerful, realistic, and generic superclass of traditional homogeneous networks (graphs).…

Autonomous agents interacting with the real world need to learn new concepts efficiently and reliably. This requires learning in a low-data regime, which is a highly challenging problem. We address this task by introducing a fast…

Recently, deep neural networks have been outperforming conventional machine learning algorithms in many computer vision-related tasks. However, it is not computationally acceptable to implement these models on mobile and IoT devices and the…

The growing gap between the increasing complexity of large language models (LLMs) and the limited computational budgets of edge devices poses a key challenge for efficient on-device inference, despite gradual improvements in hardware…

Mobile edge computing (MEC) is a promising paradigm to accommodate the increasingly prosperous delay-sensitive and computation-intensive applications in 5G systems. To achieve optimum computation performance in a dynamic MEC environment,…

Large language models (LLMs) have shown great potential in natural language processing and content generation. However, current LLMs heavily rely on cloud computing, leading to prolonged latency, high bandwidth cost, and privacy concerns.…

Training deep learning recommendation models (DLRMs) on edge workers brings several benefits, particularly in terms of data privacy protection, low latency and personalization. However, due to the huge size of embedding tables, typical DLRM…

To accelerate learning process with few samples, meta-learning resorts to prior knowledge from previous tasks. However, the inconsistent task distribution and heterogeneity is hard to be handled through a global sharing model…

Generative Artificial Intelligence (GAI) is taking the world by storm with its unparalleled content creation ability. Large Language Models (LLMs) are at the forefront of this movement. However, the significant resource demands of LLMs…