相关论文: Mobility and Cost Aware Inference Accelerating Alg…

Mobile edge computing (MEC) pushes computing resources to the edge of the network and distributes them at the edge of the mobile network. Offloading computing tasks to the edge instead of the cloud can reduce computing latency and backhaul…

Undoubtedly, Mobile Augmented Reality (MAR) applications for 5G and Beyond wireless networks are witnessing a notable attention recently. However, they require significant computational and storage resources at the end device and/or the…

With the emergence of edge computing, the problem of offloading jobs between an Edge Device (ED) and an Edge Server (ES) received significant attention in the past. Motivated by the fact that an increasing number of applications are using…

While deploying large language models on edge devices promises low-latency and privacy-preserving AI services, it is hindered by limited device resources. Although pipeline parallelism facilitates distributed inference, existing approaches…

Although multi-access edge computing (MEC) has allowed for computation offloading at the network edge, weak wireless signals in the radio access network caused by obstacles and high network load are still preventing efficient edge…

Although the computing power of mobile devices is increasing, machine learning models are also growing in size. This trend creates problems for mobile devices due to limitations like their memory capacity and battery life. While many…

Recent advancements in large language models (LLMs) have prompted interest in deploying these models on mobile devices to enable new applications without relying on cloud connectivity. However, the efficiency constraints of deploying LLMs…

The growing demand for large artificial intelligence model (LAIM) services is driving a paradigm shift from traditional cloud-based inference to edge-based inference for low-latency, privacy-preserving applications. In particular,…

We consider large scale distributed optimization over a set of edge devices connected to a central server, where the limited communication bandwidth between the server and edge devices imposes a significant bottleneck for the optimization…

This paper investigates compact large language model (LLM) deployment and world-model-assisted inference offloading in mobile edge computing (MEC) networks. We first propose an edge compact LLM deployment (ECLD) framework that jointly…

Workflow scheduling is a long-studied problem in parallel and distributed computing (PDC), aiming to efficiently utilize compute resources to meet user's service requirements. Recently proposed scheduling methods leverage the low response…

Mobile devices increasingly rely on deep neural networks (DNNs) for complex inference tasks, but running entire models locally drains the device battery quickly. Offloading computation entirely to cloud or edge servers reduces processing…

The widespread adoption of Language Models (LMs) across industries is driving interest in deploying these services across the computing continuum, from the cloud to the network edge. This shift aims to reduce costs, lower latency, and…

Mixture-of-Experts (MoE) models improve the scalability of large language models (LLMs) by activating only a small subset of relevant experts per input. However, the sheer number of expert networks in an MoE model introduces a significant…

With the prevalence of intelligent mobile applications, edge learning is emerging as a promising technology for powering fast intelligence acquisition for edge devices from distributed data generated at the network edge. One critical task…

In this paper, we investigate the scheduling design of a mobile edge computing (MEC) system, where active mobile devices with computation tasks randomly appear in a cell. Every task can be computed at either the mobile device or the MEC…

Training large language models (LLMs) at the network edge faces fundamental challenges arising from device resource constraints, severe data heterogeneity, and heightened privacy risks. To address these challenges, we propose ELSA…

Smart devices have become an indispensable part of our lives and gain increasing applicability in almost every area. Latency-aware applications such as Augmented Reality (AR), autonomous driving, and online gaming demand more resources such…

Missing data imputation (MDI) is crucial when dealing with tabular datasets across various domains. Autoencoders can be trained to reconstruct missing values, and graph autoencoders (GAE) can additionally consider similar patterns in the…

Mobile edge computing is a provisioning solution to enable Augmented Reality (AR) applications on mobile devices. AR mobile applications have inherent collaborative properties in terms of data collection in the uplink, computing at the…