Related papers: ConfigTron: Tackling network diversity with hetero…
Achieving a universally high accuracy in object detection is quite challenging, and the mainstream focus in the industry currently lies on detecting specific classes of objects. However, deploying one or multiple object detection networks…
The evolution of 5G and Beyond networks has enabled new applications with stringent end-to-end latency requirements, but providing reliable low-latency service with high throughput over public wireless networks is still a significant…
Federated Fine-Tuning (FFT) has attracted growing interest as it leverages both server- and client-side data to enhance global model generalization while preserving privacy, and significantly reduces the computational burden on edge devices…
The performance of networks that use the Internet Protocol is sensitive to precise configuration of many low-level parameters on each network device. These settings govern the action of dynamic routing protocols, which direct the flow of…
Modern deep neural network (DNN) training jobs use complex and heterogeneous software/hardware stacks. The efficacy of software-level optimizations can vary significantly when used in different deployment configurations. It is onerous and…
Most modern software systems (operating systems like Linux or Android, Web browsers like Firefox or Chrome, video encoders like ffmpeg, x264 or VLC, mobile and cloud applications, etc.) are highly-configurable. Hundreds of configuration…
The concept of SCN offers a fast framework with universal approximation guarantee for lifelong learning of non-stationary data streams. Its adaptive scope selection property enables for proper random generation of hidden unit parameters…
Modern processing networks often consist of heterogeneous servers with widely varying capabilities, and process job flows with complex structure and requirements. A major challenge in designing efficient scheduling policies in these…
The goal of machine learning is to provide solutions which are trained by data or by experience coming from the environment. Many training algorithms exist and some brilliant successes were achieved. But even in structured environments for…
Delay tolerant network (DTN) is opportunistic network where each node searches best opportunity to deliver the message called bundle to the destination. DTN implements a store and forward message switching system by simply introducing…
Traditionally, networks operate at a small fraction of their capacities; however, recent technologies, such as Software-Defined Networking, may let operators run their networks harder (i.e., at higher utilization levels). Higher utilization…
In this paper, we propose to exploit the side-tuning framework for multimodal document classification. Side-tuning is a methodology for network adaptation recently introduced to solve some of the problems related to previous approaches.…
In conventional HTTP-based adaptive streaming (HAS), a video source is encoded at multiple levels of constant bitrate representations, and a client makes its representation selections according to the measured network bandwidth. While…
This paper studies the design of self-adjusting networks whose topology dynamically adapts to the workload, in an online and demand-aware manner. This problem is motivated by emerging optical technologies which allow to reconfigure the…
Nowadays, computation is playing an increasingly more important role in the future generation of computer and communication networks, as exemplified by the recent progress in software defined networking (SDN) for wired networks as well as…
The current internet architecture is inefficient in fulfilling the demands of newly emerging internet applications. To address this issue, several over-the-top (OTT) application-level solutions have been employed, making the overall…
Driven by the advent of sophisticated and ubiquitous applications, and the ever-growing need for information, wireless networks are without a doubt steadily evolving into profoundly more complex and dynamic systems. The user demands are…
Originated from distributed learning, federated learning enables privacy-preserved collaboration on a new abstracted level by sharing the model parameters only. While the current research mainly focuses on optimizing learning algorithms and…
Distributed deep learning (DDL) training systems are designed for cloud and data-center environments that assumes homogeneous compute resources, high network bandwidth, sufficient memory and storage, as well as independent and identically…
An ever increasing number of configuration parameters are provided to system users. But many users have used one configuration setting across different workloads, leaving untapped the performance potential of systems. A good configuration…