English
Related papers

Related papers: DiffPerf: Towards Performance Differentiation and …

200 papers

Federated Learning (FL) enables decentralized training of machine learning models on distributed data while preserving privacy. However, in real-world FL settings, client data is often non-identically distributed and imbalanced, resulting…

Machine Learning · Computer Science 2025-09-18 Gergely D. Németh , Eros Fanì , Yeat Jeng Ng , Barbara Caputo , Miguel Ángel Lozano , Nuria Oliver , Novi Quadrianto

Deep neural networks with more parameters and FLOPs have higher capacity and generalize better to diverse domains. But to be deployed on edge devices, the model's complexity has to be constrained due to limited compute resource. In this…

Machine Learning · Computer Science 2019-12-02 Tianyuan Zhang , Bichen Wu , Xin Wang , Joseph Gonzalez , Kurt Keutzer

The performance of video prediction has been greatly boosted by advanced deep neural networks. However, most of the current methods suffer from large model sizes and require extra inputs, e.g., semantic/depth maps, for promising…

Computer Vision and Pattern Recognition · Computer Science 2023-03-27 Xiaotao Hu , Zhewei Huang , Ailin Huang , Jun Xu , Shuchang Zhou

Building upon Diff-A-Riff, a latent diffusion model for musical instrument accompaniment generation, we present a series of improvements targeting quality, diversity, inference speed, and text-driven control. First, we upgrade the…

Sound · Computer Science 2024-10-31 Javier Nistal , Marco Pasini , Stefan Lattner

Networking data analytics is increasingly used for enhanced network visibility and controllability. We draw the similarities between the Software Defined Networking (SDN) architecture and the MapReduce programming model. Inspired by the…

Networking and Internet Architecture · Computer Science 2016-09-13 Haoyu Song , Jun Gong , Hongfei Chen

Network data analytics are now at the core of almost every networking solution. Nonetheless, limited access to networking data has been an enduring challenge due to many reasons including complexity of modern networks, commercial…

Networking and Internet Architecture · Computer Science 2023-10-10 Nirhoshan Sivaroopan , Dumindu Bandara , Chamara Madarasingha , Guilluame Jourjon , Anura Jayasumana , Kanchana Thilakarathna

Software Defined Networking (SDN) drastically changes the meaning and process of designing, building, testing, and operating networks. The current support for wireless net- working in SDN technologies has lagged behind its development and…

Networking and Internet Architecture · Computer Science 2015-09-17 Muxi Yan , Jasson Casey , Prithviraj Shome , Alex Sprintson , Andrew Sutton

Ideally, by enabling multi-tenancy, network virtualization allows to improve resource utilization, while providing performance isolation: although the underlying resources are shared, the virtual network appears as a dedicated network to…

Networking and Internet Architecture · Computer Science 2017-05-01 Arsany Basta , Andreas Blenk , Wolfgang Kellerer , Stefan Schmid

In indoor areas such as homes and offices, high throughput communication for multiple devices is quickly becoming a necessity. Even though an access point (AP) mounted with an omni-directional antenna can cover a whole room, it cannot…

Networking and Internet Architecture · Computer Science 2020-03-05 Wei Sun

There is an increasing demand for P2P streaming in particular for layered video. In this category of applications, the stream is composed of hierarchically encoded sub-streams layers namely the base layer and enhancements layers. We…

Networking and Internet Architecture · Computer Science 2014-01-24 Abbas Bradai , Toufik Ahmed

This paper proposes a dynamic bandwidth management algorithm in which more bandwidth is allocated for higher class users and also higher priority is given to the videos with higher popularity within a class using agent technology. The…

Networking and Internet Architecture · Computer Science 2009-08-03 H S Guruprasad , H D Maheshappa

The Internet, at large, remains under the control of service providers and autonomous systems. The Internet of Things (IoT) and edge computing provide an increasing demand and potential for more user control for their web service workflows.…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-05-15 Pradeeban Kathiravelu , Peter Van Roy , Luís Veiga , Elhadj Benkhelifa

Distributed stream processing frameworks help building scalable and reliable applications that perform transformations and aggregations on continuous data streams. This paper introduces ShuffleBench, a novel benchmark to evaluate the…

Software Engineering · Computer Science 2024-03-08 Sören Henning , Adriano Vogel , Michael Leichtfried , Otmar Ertl , Rick Rabiser

Today, an increasing number of Adaptive Deep Neural Networks (AdNNs) are being used on resource-constrained embedded devices. We observe that, similar to traditional software, redundant computation exists in AdNNs, resulting in considerable…

Machine Learning · Computer Science 2022-10-24 Simin Chen , Mirazul Haque , Cong Liu , Wei Yang

Over the recent years, a significant number of complex, deep neural networks have been developed for a variety of applications including speech and face recognition, computer vision in the areas of health-care, automatic translation, image…

Performance · Computer Science 2021-11-04 Panagiotis Miliadis , Christos-Savvas Bouganis , Dionisios Pnevmatikatos

In recent years, advances in deep learning have resulted in unprecedented leaps in diverse tasks spanning from speech and object recognition to context awareness and health monitoring. As a result, an increasing number of AI-enabled…

Machine Learning · Computer Science 2019-05-20 Mario Almeida , Stefanos Laskaridis , Ilias Leontiadis , Stylianos I. Venieris , Nicholas D. Lane

HTTP-based video streaming is a key application on the Internet today, comprising the majority of Internet traffic today. Yet customers remain dissatisfied with video quality, resulting in lost revenue for content providers. Recent studies…

Networking and Internet Architecture · Computer Science 2019-01-03 Matvey Arye , Siddhartha Sen , Michael J. Freedman

Learning from data streams is among the most vital fields of contemporary data mining. The online analysis of information coming from those potentially unbounded data sources allows for designing reactive up-to-date models capable of…

Machine Learning · Computer Science 2020-10-16 Łukasz Korycki , Bartosz Krawczyk

Software defined networking (SDN) has emerged as a promising paradigm for making the control of communication networks flexible. SDN separates the data packet forwarding plane, i.e., the data plane, from the control plane and employs a…

Networking and Internet Architecture · Computer Science 2016-09-12 Andreas Blenk , Arsany Basta , Martin Reisslein , Wolfgang Kellerer

Content Delivery Networks carry the majority of Internet traffic, and the increasing demand for video content as a major IP traffic across the Internet highlights the importance of caching and prefetching optimization algorithms.…

Networking and Internet Architecture · Computer Science 2023-10-13 Nawras Alkassab , Chin-Tser Huang , Tania Lorido Botran