检索结果-内蒙古大学图书馆

Relation-Guided Representation Learning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Kang, Zhao Lu, Xiao Liang, Jian Bai, Kun Xu, Zenglin School of Computer Science and Engineering University of Electronic Science and Technology of China Sichuan China Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province Cloud and Smart Industries Group Tencent Beijing China School of Computer Science and Technology Harbin Institute of Technology Shenzhen China Center for Artificial Intelligence Peng Cheng Lab Shenzhen China

Deep auto-encoders (DAEs) have achieved great success in learning data representations via the powerful representability of neural networks. But most DAEs only focus on the most dominant structures which are able to reconstruct the data from a latent space and neglect rich latent structural information. In this work, we propose a new representation learning method that explicitly models and leverages sample relations, which in turn is used as supervision to guide the representation learning. Different from previous work, our framework well preserves the relations between samples. Since the prediction of pairwise relations themselves is a fundamental problem, our model adaptively learns them from data. This provides much flexibility to encode real data manifold. The important role of relation and representation learning is evaluated on the clustering task. Extensive experiments on benchmark data sets demonstrate the superiority of our approach. By seeking to embed samples into subspace, we further show that our method can address the large-scale and out-of-sample problem. Our source code is publicly available at: https://***/nbShawnLu/RGRL. Copyright © 2020, The Authors. All rights reserved.

关键词： Clustering algorithms

Synchronous network coding algorithm based on Galois field

学校读者我要写书评

暂无评论

Nanjing Li Gong Daxue Xuebao/Journal of Nanjing University of Science and technology 2012年第SUPPL.1期36卷 44-51页

作者： Li, Jiang Chen, Jia Li, Yi-Ning Li, Hui Shenzhen Key Lab of Cloud Computing Technology and Application Shenzhen Graduate School Peking University Shenzhen 518055 China Shenzhen Media Group Shenzhen 518055 China

A network coding(NC) algorithm based on hardware logic is presented. At first, a synchronous mechanism to solve the challenge of transmission-rate mismatch in the real network is proposed. Then a novel method to accelerate the dot product process over Galois field(GF) is designed. The whole work aims at achieving the wire speed of the hardware logic. Both encoding and decoding operations can be completed in several hundred nanoseconds. The test results show that the NC multicast communication using this algorithm can achieve the limit flow of the max-flow min-cut theorem, and the throughput is improved by using NC.

关键词： Network coding

G-MAP: General Memory-Augmented Pre-trained Language Model for Domain Tasks

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wan, Zhongwei Yin, Yichun Zhang, Wei Shi, Jiaxin Shang, Lifeng Chen, Guangyong Jiang, Xin Liu, Qun Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Science China University of Chinese Academy of Sciences China Huawei Noah's Ark Lab Hong Kong Huawei Cloud Computing Zhejiang Lab China

Recently, domain-specific PLMs have been proposed to boost the task performance of specific domains (e.g., biomedical and computer science) by continuing to pre-train general PLMs with domain-specific corpora. However, this Domain-Adaptive Pre-Training (DAPT;Gururangan et al. (2020)) tends to forget the previous general knowledge acquired by general PLMs, which leads to a catastrophic forgetting phenomenon and sub-optimal performance. To alleviate this problem, we propose a new framework of General Memory- Augmented Pre-trained Language Model (GMAP), which augments the domain-specific PLM by a memory representation built from the frozen general PLM without losing any general knowledge. Specifically, we propose a new memory-augmented layer, and based on it, different augmented strategies are explored to build the memory representation and then adaptively fuse it into the domain-specific PLM. We demonstrate the effectiveness of G-MAP on various domains (biomedical and computer science publications, news, and reviews) and different kinds (text classification, QA, NER) of tasks, and the extensive results show that the proposed G-MAP1 can achieve SOTA results on all tasks. © 2022, CC BY.

关键词： Computational linguistics

On-edge multi-task transfer learning: Model and practice with data-driven task allocation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zheng, Zimu Chen, Qiong Hu, Chuang Wang, Dan Liu, Fangming The National Engineering Research Center for Big Data Technology and System Key Laboratory of Services Computing Technology and System Ministry of Education School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China The Edge Cloud Innovation Lab. Technical Innovation Department Cloud BU Huawei Technologies Co. Ltd. Shenzhen China The Department of Computing Hong Kong Polytechnic University Kowloon Hong Kong Hong Kong

On edge devices, data scarcity occurs as a common problem where transfer learning serves as a widely-suggested remedy. Nevertheless, transfer learning imposes heavy computation burden to the resource-constrained edge devices. Existing task allocation works usually assume all submitted tasks are equally important, leading to inefficient resource allocation at a task level when directly applied in Multi-task Transfer Learning (MTL). To address these issues, we first reveal that it is crucial to measure the impact of tasks on overall decision performance improvement and quantify task importance. We then show that task allocation with task importance for MTL (TATIM) is a variant of NP-complete Knapsack problem, where the complicated computation to solve this problem needs to be conducted repeatedly under varying contexts. To solve TATIM with high computational efficiency, we propose a Data-driven Cooperative Task Allocation (DCTA) approach. Finally, we evaluate the performance of DCTA by not only a trace-driven simulation, but also a new comprehensive real-world AIOps case study which bridges model and practice via a new architecture and main components design within AIOps system. Extensive experiments show that our DCTA reduces 3.24 times of processing time, and saves 48.4% energy consumption compared with the state-of-the-art when solving TATIM. Copyright © 2021, The Authors. All rights reserved.

关键词： Energy utilization

Machine learning-based orchestration of containers: A taxonomy and future directions

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhong, Zhiheng Xu, Minxian Rodriguez, Maria Alejandra Xu, Chengzhong Buyya, Rajkumar Cloud Computing and Distributed Systems Laboratory School of Computing and Information Systems University of Melbourne Grattan Street Parkville MelbourneVICVIC 3010 Australia Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen University Town 1068 Xueyuan Avenue Guangdong Shenzhen518055 China State Key Lab of IOTSC University of Macau Avenida da Universidade Taipa 999078 China

Containerization is a lightweight application virtualization technology, providing high environmental consistency, operating system distribution portability, and resource isolation. Existing mainstream cloud service providers have prevalently adopted container technologies in their distributed system infrastructures for automated application management. To handle the automation of deployment, maintenance, autoscaling, and networking of containerized applications, container orchestration is proposed as an essential research problem. However, the highly dynamic and diverse feature of cloud workloads and environments considerably raises the complexity of orchestration mechanisms. Machine learning algorithms are accordingly employed by container orchestration systems for behavior modelling and prediction of multi-dimensional performance metrics. Such insights could further improve the quality of resource provisioning decisions in response to the changing workloads under complex environments. In this paper, we present a comprehensive literature review of existing machine learning-based container orchestration approaches. Detailed taxonomies are proposed to classify the current researches by their common features. Moreover, the evolution of machine learning-based container orchestration technologies from the year 2016 to 2021 has been designed based on objectives and metrics. A comparative analysis of the reviewed techniques is conducted according to the proposed taxonomies, with emphasis on their key characteristics. Finally, various open research challenges and potential future directions are highlighted. © 2021, CC0.

关键词： Containers

End-to-End AI-Based Point-of-Care Diagnosis System for Classifying Respiratory Illnesses and Early Detection of COVID-19

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Belkacem, Abdelkader Nasreddine Ouhbi, Sofia Lakas, Abderrahmane Benkhelifa, Elhadj Chen, Chao Department of Computer and Network Engineering CIT UAEU UAE Department of Computer Science and Software Engineering CIT UAEU UAE Cloud Computing and Applications Reseach Lab Staffordshire University United Kingdom Key Laboratory of Complex System Control Theory and Application Tianjin University of Technology China

Respiratory symptoms can be a caused by different underlying conditions, and are often caused by viral infections, such as Influenza-like illnesses or other emerging viruses like the Coronavirus. These respiratory viruses, often, have common symptoms, including coughing, high temperature, congested nose, and difficulty breathing. However, early diagnosis of the type of the virus, can be crucial, especially in cases such as the recent COVID-19 pandemic. One of the factors that contributed to the spread of the pandemic, was the late diagnosis or confusing it with regular flu-like symptoms. Science has proved that one of the possible differentiators of the underlying causes of these different respiratory diseases is coughing, which comes in different types and forms. Therefore, a reliable lab-free tool for early and more accurate diagnosis that can differentiate between different respiratory diseases is very much needed. This paper proposes an end-to-end portable system that can record data from patients with symptom, including coughs (voluntary or involuntary) and translate them into health data for diagnosis, and with the aid of machine learning, classify them into different respiratory illnesses, including COVID-19. With the ongoing efforts to stop the spread of the COVID-19 disease everywhere today, and against similar diseases in the future, our proposed low cost and user-friendly solution can play an important part in the early diagnosis. Copyright © 2020, The Authors. All rights reserved.

关键词： Diagnosis

Stable Attribute Group Editing for Reliable Few-shot Image Generation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ding, Guanqi Han, Xinzhe Wang, Shuhui Wu, Shuzhe Jin, Xin Tu, Dandan Huang, Qingming The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Peng Cheng Laboratory Shenzhen518066 China Huawei Cloud EI Innovation Lab China

Few-shot image generation aims to generate data of an unseen category based on only a few samples. Apart from basic content generation, a bunch of downstream applications hopefully benefit from this task, such as low-data detection and few-shot classification. To achieve this goal, the generated images should guarantee category retention for classification beyond the visual quality and diversity. In our preliminary work, we present an "editing-based" framework Attribute Group Editing (AGE) for reliable few-shot image generation, which largely improves the performance compared with existing methods that require re-training a GAN with limited data. Nevertheless, AGE's performance on downstream classification is not as satisfactory as expected. This paper investigates the class inconsistency problem and proposes Stable Attribute Group Editing (SAGE) for more stable class-relevant image generation. Different from AGE which directly edits from a one-shot image, SAGE takes use of all given few-shot images and estimates a class center embedding based on the category-relevant attribute dictionary. Meanwhile, according to the projection weights on the category-relevant attribute dictionary, we can select category-irrelevant attributes from the similar seen categories. Consequently, SAGE injects the whole distribution of the novel class into StyleGAN's latent space, thus largely remains the category retention and stability of the generated images. Going one step further, we find that class inconsistency is a common problem in GAN-generated images for downstream classification. Even though the generated images look photo-realistic and requires no category-relevant editing, they are usually of limited help for downstream classification. We systematically discuss this issue from both the generative model and classification model perspectives, and propose to boost the downstream classification performance of SAGE by enhancing the pixel and frequency components. Extensive experime

关键词： Generative adversarial networks

The Characterization of Multi-source Multicast with Network Coding

学校读者我要写书评

暂无评论

The Characterization of Multi-source Multicast with Network ...

2012 IEEE 14th International Conference on Communication technology

作者： Hanxu Hou Hui Li Shenzhen Key Lab of Cloud Computing Technology & Application Shenzhen Graduate SchoolPeking University Shenzhen Eng.Lab of Converged Network Tech.Shenzhen Graduate SchoolPeking University

ISBN: (纸本)9781467321006

The capacity region of the single-source multicast network coding has an explicit Max-flow Min-cut *** for multi-source multicast networks the problem is still *** this paper,we mainly discuss the case of independent encoding multi-source multicast network using inter-session network *** propose a multi-source independent encoding theorem for this problem which characterizes the admissible coding rate region of independent encoding for relevant multiple *** theorem is proposed by the paper according to the strongly typical sequences and random *** also point out the connections between our theorem and the general multi- source network coding problem,of which the results are computable and can be used to design the multi-source network coding algorithm.

关键词： network coding multi-source multicast correlated data computable

Structure of campus network based on reconfigurable architecture

学校读者我要写书评

暂无评论

Tongxin Xuebao/Journal on Communications 2013年第SUPPL.2期34卷 107-110页

作者： Yuan, Hu-Sheng Feng, Hua Li, Hui Zhong, Zhi-Bin Pan, Kai Network and Information Center of Shenzhen University Town Shenzhen 518055 China Peking University Shenzhen Graduate School Shenzhen 518055 China Shenzhen Key Lab. of Cloud Computing Technology and Application Shenzhen 518055 China Shenzhen Engineering Lab. of Converged Network Technology Shenzhen 518055 China Huaqiang Vocational Technical School Shenzhen 518000 China

Because of the petrifaction of the existing network, it is difficult to achieve the controllability, adaptability and expansibility in current structure. Simultaneously, in order to have better campus network services in teaching, researching and studying, a new structure based on reconfigurable architecture for campus network was designed based on service set handling capacity of various kinds of business in reconfigurable network as the central idea. After the evolution from tradition to flat structure, a more condensed structure was proposed by adopting virtualization technology on switches and routers. It has the advantages of high performance, high reliability, manageability and augmentability.

关键词： Virtualization