Related papers: Ensuring domain consistency in an adaptive framewo…
Deep learning has become an indispensable part of life, such as face recognition, NLP, etc., but the training of deep model has always been a challenge, and in recent years, the complexity of training data and models has shown explosive…
The increasing device heterogeneity and decentralization requirements in the computing continuum (i.e., spanning edge, fog, and cloud) introduce new challenges in resource orchestration. In such environments, agents are often responsible…
The parallel and distributed processing are becoming de facto industry standard, and a large part of the current research is targeted on how to make computing scalable and distributed, dynamically, without allocating the resources on…
This work studies a well-known shared-cache coded caching scenario where each cache can serve an arbitrary number of users, analyzing the case where there is some knowledge about such number of users (i.e., the topology) during the content…
Domain-Specific Languages (DSLs) improve programmers productivity by decoupling problem descriptions from algorithmic implementations. However, DSLs for High-Performance Computing (HPC) have two additional critical requirements: performance…
Domain adaptation is crucial in many real-world applications where the distribution of the training data differs from the distribution of the test data. Previous Deep Learning-based approaches to domain adaptation need to be trained jointly…
For popular websites most important concern is to handle incoming load dynamically among web servers, so that they can respond to their client without any wait or failure. Different websites use different strategies to distribute load among…
More widespread adoption requires swarms of robots to be more flexible for real-world applications. Multiple challenges remain in complex scenarios where a large amount of data needs to be processed in real-time and high degrees of…
The massive growth in the utilization of edge AI has made the applications of machine learning models ubiquitous in different domains. Despite the computation and communication efficiency of these systems, due to limited computation…
A fundamental challenge in large-scale cloud networks and data centers is to achieve highly efficient server utilization and limit energy consumption, while providing excellent user-perceived performance in the presence of uncertain and…
Today's data centers have an abundance of computing resources, hosting server clusters consisting of as many as tens or hundreds of thousands of machines. To execute a complex computing task over a data center, it is natural to distribute…
Super-resolution is widely used in medical imaging to enhance low-quality data, reducing scan time and improving abnormality detection. Conventional super-resolution approaches typically rely on paired datasets of downsampled and original…
Deep learning (DL) has transformed applications in a variety of domains, including computer vision, natural language processing, and tabular data analysis. The search for improved DL model accuracy has led practitioners to explore…
Dynamic mode decomposition (DMD) provides a principled approach to extract physically interpretable spatial modes from time-resolved flow field data, along with a linear model for how the amplitudes of these modes evolve in time. Recently,…
Streamflow forecasts are critical to guide water resource management, mitigate drought and flood effects, and develop climate-smart infrastructure and governance. Many global regions, however, have limited streamflow observations to guide…
The performance of computer networks relies on how bandwidth is shared among different flows. Fair resource allocation is a challenging problem particularly when the flows evolve over time.To address this issue, bandwidth sharing techniques…
The decode-forward achievable region is studied for general networks. The region is subject to a fundamental tension in which nodes individually benefit at the expense of others. The complexity of the region depends on all the ways of…
With the ever-increasing range of applications of Internet in Things (IoT) and sensor networks, challenges are emerging in various categories of classification tasks. Applications such as vehicular networking, UAV swarm coordination and…
Single-source domain generalization for crowd counting is highly challenging because a single labeled source domain may contain heterogeneous latent domains, while unseen target domains often exhibit severe distribution shifts. A central…
As the complexity of our neural network models grow, so too do the data and computation requirements for successful training. One proposed solution to this problem is training on a distributed network of computational devices, thus…