相关论文: Outsourcing Training without Uploading Data via Ef…

Deep learning has gained broad interest in remote sensing image scene classification thanks to the effectiveness of deep neural networks in extracting the semantics from complex data. However, deep networks require large amounts of training…

Data-Free Knowledge Distillation (DFKD) is a novel task that aims to train high-performance student models using only the pre-trained teacher network without original training data. Most of the existing DFKD methods rely heavily on…

The increasing deployment of sensor networks, ranging from home networks to industrial automation, leads to a similarly growing demand for storing and processing the collected sensor data. To satisfy this demand, the most promising approach…

Federated learning (FL) enables collaborative learning without data centralization but introduces significant communication costs due to multiple communication rounds between clients and the server. One-shot federated learning (OSFL)…

Diffusion-based generative models have become dominant generators of high-fidelity images and videos but remain limited by their computationally expensive inference procedures. Existing acceleration techniques either require extensive model…

Computation offloading becomes useful for users of limited computing power and mobile edge computing (MEC) can help mobile users perform their tasks more effectively. In this paper, we consider MEC when users perform tasks with local data…

Distributed training techniques have been widely deployed in large-scale deep neural networks (DNNs) training on dense-GPU clusters. However, on public cloud clusters, due to the moderate inter-connection bandwidth between instances,…

We describe a system for serverless computing where users, programs, and the underlying platform share a common representation of a computation: a deterministic procedure, run in an environment of well-specified data or the outputs of other…

The heterogeneous edge-cloud computing paradigm can provide a more optimal direction to deploy scientific workflows than traditional distributed computing or cloud computing environments. Due to the different sizes of scientific datasets…

Data intensive applications often involve the analysis of large datasets that require large amounts of compute and storage resources. While dedicated compute and/or storage farms offer good task/data throughput, they suffer low resource…

Edge computing is the natural progression from Cloud computing, where, instead of collecting all data and processing it centrally, like in a cloud computing environment, we distribute the computing power and try to do as much processing as…

Modern deep learning systems require huge data sets to achieve impressive performance, but there is little guidance on how much or what kind of data to collect. Over-collecting data incurs unnecessary present costs, while under-collecting…

Model extraction aims to create a functionally similar copy from a machine learning as a service (MLaaS) API with minimal overhead, typically for illicit profit or as a precursor to further attacks, posing a significant threat to the MLaaS…

Federated Learning (FL) has been considered as an appealing framework to tackle data privacy issues of mobile devices compared to conventional Machine Learning (ML). Using Edge Servers (ESs) as intermediaries to perform model aggregation in…

Scavenging the idling computation resources at the enormous number of mobile devices can provide a powerful platform for local mobile cloud computing. The vision can be realized by peer-to-peer cooperative computing between edge devices,…

Current serverless platforms struggle to optimize resource utilization due to their dynamic and fine-grained nature. Conventional techniques like overcommitment and autoscaling fall short, often sacrificing utilization for practicability or…

Open-set Semi-supervised Learning (OSSL) holds a realistic setting that unlabeled data may come from classes unseen in the labeled set, i.e., out-of-distribution (OOD) data, which could cause performance degradation in conventional SSL…

Edge computing brings a new paradigm in which the sharing of computing, storage, and bandwidth resources as close as possible to the mobile devices or sensors generating a large amount of data. A parallel trend is the rise of phones and…

Offline model-based optimization aims to find a design that maximizes a property of interest using only an offline dataset, with applications in robot, protein, and molecule design, among others. A prevalent approach is gradient ascent,…

Federated learning has recently emerged as a paradigm promising the benefits of harnessing rich data from diverse sources to train high quality models, with the salient features that training datasets never leave local devices. Only model…