检索结果-内蒙古大学图书馆

iGniter: Interference-Aware GPU Resource Provisioning for Predictable DNN Inference in the Cloud

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xu, Fei Xu, Jianian Chen, Jiabin Chen, Li Shang, Ruitao Zhou, Zhi Liu, Fangming The Shanghai Key Laboratory of Multidimensional Information Processing School of Computer Science and Technology East China Normal University 3663 N. Zhongshan Road Shanghai200062 China The School of Computing and Informatics University of Louisiana at Lafayette 301 East Lewis Street LafayetteLA70504 United States The Guangdong Key Laboratory of Big Data Analysis and Processing School of Computer Science and Engineering Sun Yat-sen University 132 E. Waihuan Road Guangzhou510006 China The National Engineering Research Center for Big Data Technology and System The Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology 1037 Luoyu Road Wuhan430074 China

GPUs are essential to accelerating the latency-sensitive deep neural network (DNN) inference workloads in cloud datacenters. To fully utilize GPU resources, spatial sharing of GPUs among co-located DNN inference workloads becomes increasingly compelling. However, GPU sharing inevitably brings severe performance interference among co-located inference workloads, as motivated by an empirical measurement study of DNN inference on EC2 GPU instances. While existing works on guaranteeing inference performance service level objectives (SLOs) focus on either temporal sharing of GPUs or reactive GPU resource scaling and inference migration techniques, how to proactively mitigate such severe performance interference has received comparatively little attention. In this paper, we propose iGniter, an interference-aware GPU resource provisioning framework for cost-efficiently achieving predictable DNN inference in the cloud. iGniter is comprised of two key components: (1) a lightweight DNN inference performance model, which leverages the system and workload metrics that are practically accessible to capture the performance interference;(2) A cost-efficient GPU resource provisioning strategy that jointly optimizes the GPU resource allocation and adaptive batching based on our inference performance model, with the aim of achieving predictable performance of DNN inference workloads. We implement a prototype of iGniter based on the NVIDIA Triton inference server hosted on EC2 GPU instances. Extensive prototype experiments on four representative DNN models and datasets demonstrate that iGniter can guarantee the performance SLOs of DNN inference workloads with practically acceptable runtime overhead, while saving the monetary cost by up to 25% in comparison to the state-of-the-art GPU resource provisioning strategies. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

Searching for a new probability distribution for modeling non-scale-free heavy-tailed real-world networks

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2022年

作者： Chakraborty, Tanujit Chattopadhyay, Swarup Das, Suchismita Kumar, Uttam Jayavelu, Senthilnath Spatial Computing Laboratory Center for Data Sciences International Institute of Information Technology Bangalore560100 India Machine Intelligence Unit Indian Statistical Institute Kolkata700108 India Department of Data Science S P Jain School of Global Management Mumbai400070 India Institute for Infocomm Research Agency for Science Technology and Research 138632 Singapore

Perhaps the most controversial topic in network science research is whether real-world complex networks are scale-free or not. Recently, Broido and Clauset [A.D. Broido, A. Clauset, Nature Communication, 10, 1017 (2019)] claimed that the degree distributions of real-world networks are rarely power-law under statistical tests. Such complex networks include social, biological, information, temporal, and brain networks are often heavy-tailed where the assumption on scale-free nature of real-world heavy-tailed networks becomes insignificant so as the complex system evolves over time. The failure of power-law distribution in fitting the degree distribution data is mainly due to the presence of an identifiable non-linearity in the entire degree distribution in a log-log scale of a heavy-tailed complex network. Here, we attempt to address this issue by proposing a new class of heavy-tailed probability distributions, for modeling the entire degree distributions of complex networks and capturing the non-linearity of these heavy-tailed networks. The generalized Lomax Model is introduced to fit the degree distributions of non-scale-free real-world networks and applied to model a wide variety of large-scale real-world complex networks. Several statistical properties of the proposed model, such as extreme value and inferential statistical properties are derived into this context. Rigorous experimental analysis showcases the excellent performance of the proposed family of distributions while fitting the heavy-tailed real-world complex networks over fifty real-world data sets in comparison with the state-of-the-art. © 2022, CC BY.

关键词： Statistical mechanics

Engineering Interactive Systems Embedding AI Technologies (3rd workshop on)

学校读者我要写书评

暂无评论

Engineering Interactive Systems Embedding AI Technologies (3...

Companion Proceedings of the 17th ACM SIGCHI Symposium on Engineering Interactive computing Systems

作者： Barbara Rita Barricelli José Creissac Campos Kris Luyten Sven Mayer Philippe Palanque Emanuele Panizzi Lucio Davide Spano Simone Stumpf Department of Information Engineering Università degli Studi di Brescia Brescia Italy Departamento de Informática Universidade do Minho Braga Portugal Expertise Centre for Digital Media Hasselt University - tUL - Flanders Make Diepenbeek Belgium TU Dortmund University Dortmund Germany and Research Center Trustworthy Data Science and Security Dortmund Germany ICS-IRIT University of Toulouse Toulouse France Sapienza University Rome Italy Department of Mathematics and Computer Science University of Cagliari Cagliari Italy School of Computing Science University of Glasgow Glasgow United Kingdom

Fully Synthetic Videos and Random Background-Pasting Method for Flame Segmentation

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Jia, Yang Zhang, Xinmeng Kuang, Yaxi Chen, Yanping Wang, Gang Zhang, Qixing School of Computer Science Xi'an University of Posts and Telecommunications 710121 China Shaanxi Key Laboratory of Network Data Intelligent Processing Xi'an University of Posts and Telecommunications 710121 China Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'an University of Posts and Telecommunications 710121 China School of Information Science and Technology University of Science and Technology of China 230026 China XNIF262 710061 China State Key Laboratory of Fire Science University of Science and Technology of China 230026 China

Video-based flame detection (VFD) aims to recognize fire events by the image features. Flame segmentation is an essential task in VFD, which provides suspected regions for feature analysis and object recognition. The development of deep learning has promoted VFD performances to a higher level. However, due to the rarity of recorded fire events, it is challenging to get tremendous positive flame samples for model training. Existing deep learning-based VFD methods are limited to the lack of flame samples under different scenarios. In this paper, we propose an assumption that we can train a segmentation model with virtual flame images and design experiments to prove it. We take many virtual flame videos to extend existing flame datasets, which provide adequate flame samples for deep learning-based VFD methods. We also take a random background-pasting method to distribute the flame images among different scenarios. The proposed method trains a flame segmentation model with zero real flame image. Moreover, we perform segmentation testing with real flame images, which the model has never touched, to see if the model trained with ‘fake’ images can segment real objects. We trained four segmentation models based on FCN, U-Net, Deeplabv3, and Mask-RCNN with synthetic flame video frames, and obtained the highest mPA of 0.783 and mIoU of 0.515. The experimental results on FIRE-SMOKE-dataSET and Fire-Detection-Image-dataset demonstrate that the ‘fake’ flame samples generated by the proposed random background-pasting method can improve the performances of existing state-of-the-art flame segmentation methods obviously on cross-dataset evaluation settings. © 2022, The Authors. All rights reserved.

关键词： Deep learning

A novel binary modified beluga whale optimization algorithm using ring crossover and probabilistic state mutation for enhanced bladder cancer diagnosis

学校读者我要写书评

暂无评论

Informatics in Medicine Unlocked 2024年 50卷

作者： Gharaibeh, Hasan Alawad, Noor Aldeen Nasayreh, Ahmad Al Mamlook, Rabia Emhamed Makhadmeh, Sharif Naser Bashkami, Ayah Abualigah, Laith Ezugwu, Absalom E. Computer Science Department Faculty of Information Technology and Computer Sciences Yarmouk University Irbid 21163 Jordan Department of Business Administration Trine University IN United States Department of Mechanical and Industrial Engineering University of Zawia Tripoli Libya Department of Information Technology King Abdullah II School of Information Technology The University of Jordan Amman 11942 Jordan Department Medical Laboratory Sciences – Faculty of Science Al Balqa Applied University Salt 19117 Jordan Department of Cyber Security and Cloud Computing Faculty of Information Technology Applied Science Private University Amman 11937 Jordan Artificial Intelligence and Sensing Technologies (AIST) Research Center University of Tabuk Tabuk 71491 Saudi Arabia Computer Science Department Al al-Bayt University Mafraq 25113 Jordan MEU Research Unit Middle East University Amman 11831 Jordan Applied science research center Applied science private university Amman 11931 Jordan Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura 140401 India Unit for Data Science and Computing North-West University 11 Hofman Street Potchefstroom 2520 South Africa Artificial Intelligence Research Center (AIRC) College of Engineering and Information Technology Ajman University Ajman P.O. Box 346 United Arab Emirates

Bladder cancer (BC) remains a significant global health challenge, requiring the development of accurate predictive models for diagnosis. In this study, a new Binary Modified White Whale Optimization (B-MBWO) algorithm is proposed to address the BC problem. The proposed method utilizes circular transitivity optimization and the Probabilistic State Mutation Algorithm (PSMA) to enhance its optimization performance. The new method is called the BBWORCPS algorithm. High-dimensional and complex medical datasets pose challenges to the original optimization algorithms in addressing the BC problem, motivating the proposed modifications to the original Beluga Whale Optimization algorithm. These enhancements, including quantum-inspired mutation and circular crossing, aim to improve solution space exploration and enhance the algorithm's effectiveness in handling intricate feature spaces. Through comprehensive experiments on BC datasets, the superiority of the BBWORCPS algorithm in terms of feature selection accuracy and computational efficiency is demonstrated compared to existing optimization methods. The obtained findings suggest that BBWORCPS offers a promising approach for developing more precise and reliable predictive models for bladder cancer analysis. © 2024 The Author(s)

关键词： Binary modified beluga whale optimization Bladder cancer Feature selection Machine learning Predictive modeling

Multi-View Mutual Learning Network for Multimodal Fake News Detection

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Cui, Wei Zhang, Xuerui Shang, Mingsheng College of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China School of Electronic Information and Communication Engineering Chongqing Aerospace Polytechnic Chongqing400021 China

Multimodal fake news is more deceptive than unimodal content and often has adverse social and economic impacts. However, most existing methods learn modal features from a single perspective, without considering simultaneously learning and sharing knowledge across modalities from different perspectives. Our work presents a novel Multi-View Mutual Learning (MVML) network for multimodal fake news detection, which explores the semantic relationship between words and scenes, as well as words and objects, and investigates the semantic connection that exists between global concepts and local objects from multiple perspectives. We first construct text-scenes and text-objects graphs respectively, and perform intra-graph inference to obtain multi-view features. Then, the multi-view fusion layer based on the cross-view attention mechanism interactively models the cross-view dependencies between the image and text. The extracted features before feeding into the final classifier are further processed via a feed-forward attention module, which adaptively reweights and aggregates the features for redundancy reduction. In addition, to exploit the respective advantages of two multi-view classifiers, we propose a mutual learning mechanism that allows them to perform knowledge distillation and align the learning targets. The proposed MVML is thoroughly assessed on four publicly available benchmark datasets, and the findings demonstrate that it outperforms the existing standard approaches. © 2023, The Authors. All rights reserved.

关键词： Semantics

Evaluating Interpolation and Extrapolation Performance of Neural Retrieval Models

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhan, Jingtao Xie, Xiaohui Mao, Jiaxin Liu, Yiqun Guo, Jiafeng Zhang, Min Ma, Shaoping Department of Computer Science and Technology Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China Beijing Key Laboratory of Big Data Management and Analysis Methods Gaoling School of Artificial Intelligence Renmin University of China Beijing100872 China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

A retrieval model should not only interpolate the training data but also extrapolate well to the queries that are different from the training data. While neural retrieval models have demonstrated impressive performance on ad-hoc search benchmarks, we still know little about how they perform in terms of interpolation and extrapolation. In this paper, we demonstrate the importance of separately evaluating the two capabilities of neural retrieval models. Firstly, we examine existing ad-hoc search benchmarks from the two perspectives. We investigate the distribution of training and test data and find a considerable overlap in query entities, query intent, and relevance labels. This finding implies that the evaluation on these test sets is biased toward interpolation and cannot accurately reflect the extrapolation capacity. Secondly, we propose a novel evaluation protocol to separately evaluate the interpolation and extrapolation performance on existing benchmark datasets. It resamples the training and test data based on query similarity and utilizes the resampled dataset for training and evaluation. Finally, we leverage the proposed evaluation protocol to comprehensively revisit a number of widely-adopted neural retrieval models. Results show models perform differently when moving from interpolation to extrapolation. For example, representation-based retrieval models perform almost as well as interaction-based retrieval models in terms of interpolation but not extrapolation. Therefore, it is necessary to separately evaluate both interpolation and extrapolation performance and the proposed resampling method serves as a simple yet effective evaluation tool for future IR studies. Copyright © 2022, The Authors. All rights reserved.

关键词： Extrapolation

MFCLIP: Multi-modal Fine-grained CLIP for Generalizable Diffusion Face Forgery Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Yaning Wang, Tianyi Yu, Zitong Gao, Zan Shen, Linlin Chen, Shengyong Jinan250353 China Nanyang Technological University 50 Nanyang Ave Block N 4 639798 Singapore School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Jinan250014 China The Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin300384 China Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

The rapid development of photo-realistic face generation methods has raised significant concerns in society and academia, highlighting the urgent need for robust and generalizable face forgery detection (FFD) techniques. Although existing approaches mainly capture face forgery patterns using image modality, other modalities like fine-grained noises and texts are not fully explored, which limits the generalization capability of the model. In addition, most FFD methods tend to identify facial images generated by GAN, but struggle to detect unseen diffusion-synthesized ones. To address the limitations, we aim to leverage the cutting-edge foundation model, contrastive language-image pre-training (CLIP), to achieve generalizable diffusion face forgery detection (DFFD). In this paper, we propose a novel multi-modal fine-grained CLIP (MFCLIP) model, which mines comprehensive and fine-grained forgery traces across image-noise modalities via language-guided face forgery representation learning, to facilitate the advancement of DFFD. Specifically, we devise a fine-grained language encoder (FLE) that extracts fine global language features from hierarchical text prompts. We design a multi-modal vision encoder (MVE) to capture global image forgery embeddings as well as fine-grained noise forgery patterns extracted from the richest patch, and integrate them to mine general visual forgery traces. Moreover, we build an innovative plug-and-play sample pair attention (SPA) method to emphasize relevant negative pairs and suppress irrelevant ones, allowing cross-modality sample pairs to conduct more flexible alignment. Extensive experiments and visualizations show that our model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations. Copyright © 2024, The Authors. All rights reserved.

关键词： Alignment

Engineering Software Systems for Quantum computing as a Service: A Mapping Study

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ahmad, Aakash Waseem, Muhammad Liang, Peng Fehmideh, Mahdi Khan, Arif Ali Reichelt, David Georg Mikkonen, Tommi School of Computing and Communications Lancaster University Leipzig Leipzig Germany Faculty of Information Technology University of Jyväskylä Jyväskylä Finland School of Computer Science Wuhan University Wuhan China School of Business University of Southern Queensland QLD Australia M3S Empirical Software Engineering Research Unit University of Oulu Oulu Finland

Quantum systems have started to emerge as a disruptive technology and enabling platforms-exploiting the principles of quantum mechanics-to achieve quantum supremacy in computing. Academic research, industrial projects (e.g., Amazon Braket), and consortiums like 'Quantum Flagship' are striving to develop practically capable and commercially viable quantum computing (QC) systems and technologies. Quantum computing as a Service (QCaaS) is viewed as a solution attuned to the philosophy of service-orientation that can offer QC resources and platforms, as utility computing, to individuals and organisations who do not own quantum computers. To understand the quantum service development life cycle and pinpoint emerging trends, we used evidence-based software engineering approach to conduct a systematic mapping study (SMS) of research that enables or enhances QCaaS. The SMS process retrieved a total of 55 studies, and based on their qualitative assessment we selected 9 of them to investigate (i) the functional aspects, design models, patterns, programming languages, deployment platforms, and (ii) trends of emerging research on QCaaS. The results indicate three modelling notations and a catalogue of five design patterns to architect QCaaS, whereas Python (native code or frameworks) and Amazon Braket are the predominant solutions to implement and deploy QCaaS solutions. From the quantum software engineering (QSE) perspective, this SMS provides empirically grounded findings that could help derive processes, patterns, and reference architectures to engineer software services for QC. © 2023, CC BY.

关键词： Life cycle