Related papers: Delta: A Cloud-assisted Data Enrichment Framework …

Non-Centralized Continual Learning (NCCL) has become an emerging paradigm for enabling distributed devices such as vehicles and servers to handle streaming data from a joint non-stationary environment. To achieve high reliability and…

With privacy as a motivation, Federated Learning (FL) is an increasingly used paradigm where learning takes place collectively on edge devices, each with a cache of user-generated training examples that remain resident on the local device.…

We propose a novel framework and a solution to tackle the continual learning (CL) problem with changing network architectures. Most CL methods focus on adapting a single architecture to a new task/class by modifying its weights. However,…

When facing changing environments in the real world, the lightweight model on client devices suffers from severe performance drops under distribution shifts. The main limitations of the existing device model lie in (1) unable to update due…

As the quantity and complexity of information processed by software systems increase, large-scale software systems have an increasing requirement for high-performance distributed computing systems. With the acceleration of the Internet in…

This letter proposes two novel proactive cooperative caching approaches using deep learning (DL) to predict users' content demand in a mobile edge caching network. In the first approach, a (central) content server takes responsibilities to…

Fast model updates for unseen tasks on intelligent edge devices are crucial but also challenging due to the limited computational power. In this paper,we propose MetaLDC, which meta-trains braininspired ultra-efficient low-dimensional…

The conventional cloud-based large model learning framework is increasingly constrained by latency, cost, personalization, and privacy concerns. In this survey, we explore an emerging paradigm: collaborative learning between on-device small…

An increasing number of mobile applications rely on Machine Learning (ML) routines for analyzing data. Executing such tasks at the user devices saves the energy spent on transmitting and processing large data volumes at distant…

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…

Existing Continual Learning (CL) solutions only partially address the constraints on power, memory and computation of the deep learning models when deployed on low-power embedded CPUs. In this paper, we propose a CL solution that embraces…

Deep learning (DL) compilers rely on cost models and auto-tuning to optimize tensor programs for target hardware. However, existing approaches depend on large offline datasets, incurring high collection costs and offering suboptimal…

With the growth of Internet of Things (IoT) and mo-bile edge computing, billions of smart devices are interconnected to develop applications used in various domains including smart homes, healthcare and smart manufacturing. Deep learning…

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…

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,…

With the digitization of modern cities, large data volumes and powerful computational resources facilitate the rapid update of intelligent models deployed in smart cities. Continual learning (CL) is a novel machine learning paradigm that…

Cognitive diagnosis is an essential research topic in intelligent education, aimed at assessing the level of mastery of different skills by students. So far, many research works have used deep learning models to explore the complex…

Meta-Continual Learning (Meta-CL) enables models to learn new classes from limited labelled samples, making it promising for IoT applications where manual labelling is costly. However, existing studies focus on accuracy while ignoring…

As a promising distributed machine learning paradigm, Federated Learning (FL) enables all the involved devices to train a global model collaboratively without exposing their local data privacy. However, for non-IID scenarios, the…

In our increasingly interconnected world, where intelligent devices continually amass copious personalized multi-modal data, a pressing need arises to deliver high-quality, personalized device-aware services. However, this endeavor presents…