Related papers: Enhancing User Experience in On-Device Machine Lea…
To overcome the burden on the memory size and bandwidth due to ever-increasing size of large language models (LLMs), aggressive weight quantization has been recently studied, while lacking research on quantizing activations. In this paper,…
Nowadays, data caching is being used as a high-speed data storage layer in mobile edge computing networks employing flow control methodologies at an exponential rate. This study shows how to discover the best architecture for backhaul…
Model compression is a critical technique to efficiently deploy neural network models on mobile devices which have limited computation resources and tight power budgets. Conventional model compression techniques rely on hand-crafted…
Vertical Cavity Surface Emitting Lasers (VCSELs) have gained popularity in Optical Wireless Communication (OWC) due to their high modulation bandwidth, narrow spectral width, and directional beam, offering improved spectral efficiency and…
Machine learning (ML) can be used in various ways to improve multi-user multiple-input multiple-output (MU-MIMO) receive processing. Typical approaches either augment a single processing step, such as symbol detection, or replace multiple…
A promising technique to provide mobile applications with high computation resources is to offload the processing task to the cloud. Utilizing the abundant processing capabilities of the clouds, mobile edge computing enables mobile devices…
In this paper, the concept of Machine Learning (ML) is introduced to the Orthogonal Frequency Division Multiple Access-based (OFDMA-based) scheduler. Similar to the impact of the Channel Quality Indicator (CQI) on the scheduler in the Long…
Personal mobile sensing is fast permeating our daily lives to enable activity monitoring, healthcare and rehabilitation. Combined with deep learning, these applications have achieved significant success in recent years. Different from…
Optimal power flow (OPF) has been used for real-time grid operations. Prior efforts demonstrated that utilizing flexibility from dynamic topologies will improve grid efficiency. However, this will convert the linear OPF into a mixed-integer…
To facilitate the evolution of edge intelligence in ever-changing environments, we study on-device incremental learning constrained in limited computation resource in this paper. Current on-device training methods just focus on efficient…
It is commonly assumed that the end-to-end networking performance of edge offloading is purely dictated by that of the network connectivity between end devices and edge computing facilities, where ongoing innovation in 5G/6G networking can…
Recent years have witnessed the prevailing progress of Generative Adversarial Networks (GANs) in image-to-image translation. However, the success of these GAN models hinges on ponderous computational costs and labor-expensive training data.…
Federated Learning (FL) is commonly used in systems with distributed and heterogeneous devices with access to varying amounts of data and diverse computing and storage capacities. FL training process enables such devices to update the…
Federated Learning (FL) has emerged as a privacy-preserving paradigm for training machine learning models across distributed edge devices in the Internet of Things (IoT). By keeping data local and coordinating model training through a…
Transformer-based models excel in speech recognition. Existing efforts to optimize Transformer inference, typically for long-context applications, center on simplifying attention score calculations. However, streaming speech recognition…
Latency to end-users and regulatory requirements push large companies to build data centers all around the world. The resulting data is "born" geographically distributed. On the other hand, many machine learning applications require a…
A prevailing approach for learning visuomotor policies is to employ reinforcement learning to map high-dimensional visual observations directly to action commands. However, the combination of high-dimensional visual inputs and agile…
Upon deployment to edge devices, it is often desirable for a model to further learn from streaming data to improve accuracy. However, extracting representative features from such data is challenging because it is typically unlabeled,…
Traditional Retrieval-Augmented Generation (RAG) approaches generally assume that retrieval and generation occur on powerful servers removed from the end user. While this reduces local hardware constraints, it introduces significant…
Federated learning (FL) enables distributed model training, yet in heterogeneous deployments, Bandwidth-Constrained Clients (BCCs) often contribute inefficiently due to limited uplink bandwidth. In model-heterogeneous FL with fixed small…