检索结果-内蒙古大学图书馆

IEEE International Conference on data Mining (ICDM)

作者： Yangcheng Gao Zhao Zhang Haijun Zhang Mingbo Zhao Yi Yang Meng Wang School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China Harbin Institute of Technology (Shenzhen) Xili University Town Shenzhen China City University of Hong Kong Hong Kong SAR Centre for Artificial Intelligence University of Technology Sydney Sydney NSW Australia

ISBN: (纸本)9781665423991

Deep neural network (DNN) compression can reduce the memory footprint of deep networks effectively, so that the deep model can be deployed on the portable devices. However, most of the existing model compression methods cost lots of time, e.g., vector quantization or pruning, which makes them inept to the real-world applications that need fast online computation. In this paper, we therefore explore how to accelerate the model compression process by reducing the computation cost. Then, we propose a new deep model compression method, termed Dictionary Pair-based data-Free Fast DNN Compression, which aims at reducing the memory consumption of DNNs without extra training and can greatly improve the compression efficiency. Specifically, our proposed method performs tensor decomposition on the DNN model with a fast dictionary pair learning-based reconstruction approach, which can be deployed on different layers (e.g., convolution and fully-connection layers). Given a pre-trained DNN model, we first divide the parameters (i.e., weights) of each layer into a series of partitions for dictionary pair-based fast reconstruction, which can potentially discover more fine-grained information and provide the possibility for parallel model compression. Then, dictionaries of less memory occupation are learned to reconstruct the weights. Extensive experiments on popular DNNs (i.e., VGG-16, ResNet-18 and ResNet-50) showed that our proposed weight compression method can significantly reduce the memory footprint and speed up the compression process, with less performance loss.

关键词： Deep learning Training Performance evaluation Dictionaries Tensors Costs Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Structure-aware random fourier kernel for graphs 21

Structure-aware random fourier kernel for graphs

引用

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Jinyuan Fang Qiang Zhang Zaiqiao Meng Shangsong Liang School of Computer Science and Engineering Sun Yat-sen University China and Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Hangzhou Innovation Center Zhejiang University China and College of Computer Science and Technology Zhejiang University China and AZFT Knowledge Engine Lab China School of Computing Science University of Glasgow United Kingdom and Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates School of Computer Science and Engineering Sun Yat-sen University China and Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China and Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates

ISBN: (纸本)9781713845393

Gaussian Processes (GPs) define distributions over functions and their generalization capabilities depend heavily on the choice of kernels. In this paper, we propose a novel structure-aware random Fourier (SRF) kernel for GPs that brings several benefits when modeling graph-structured data. First, SRF kernel is defined with a spectral distribution based on the Fourier duality given by the Bochner's theorem, transforming the kernel learning problem to a distribution inference problem. Second, SRF kernel admits a random Fourier feature formulation that makes the kernel scalable for optimization. Third, SRF kernel enables to leverage geometric structures by taking subgraphs as inputs. To effectively optimize GPs with SRF kernel, we develop a variational EM algorithm, which alternates between an inference procedure (E-step) and a learning procedure (M-step). Experimental results on five real-world datasets show that our model can achieve state-of-the-art performance in two typical graph learning tasks, i.e., object classification and link prediction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Weighted partial order oriented three-way decisions under score-based common voting rules

引用

International Journal of Approximate Reasoning 2020年 123卷 41-54页

作者： Li, Lei Wu, Xindong Chen, Huanhuan Zhou, Chuan Liu, Guanfeng Jiang, Yongkang Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology) Ministry of Education Hefei 230601 China Mininglamp Academy of Sciences Mininglamp Technologies Beijing 100084 China School of Computer Science and Technology University of Science and Technology of China Hefei 230026 China Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing 100190 China Computing Dept Macquarie University Sydney A1C 5S7 Australia

Recently, with the trisecting and acting models of human cognitive behaviors, three-way decisions are introduced to deal with uncertain decisions in many applications. To define and conduct the three-way decisions on the possible or necessary loser or co-loser and/or winner or co-winner, we first define the score-based common voting rules, where a score-based function is introduced to evaluate certain utility, including positional scoring rules, maximin, Bucklin, and so on. Then on one hand, it has been proved that under certain conditions three-way decisions on the possible loser or co-loser and/or winner or co-winner are NP-complete with positional scoring rules, maximin, and Bucklin, respectively. On the other hand, we have presented algorithms whose time complexity is polynomial to conduct three-way decisions on the necessary winner or co-winner and/or necessary loser or co-loser with positional scoring rules, maximin, and Bucklin in time O(nm²), O(nm³), and O(nm²), respectively, which has been validated experimentally. © 2020 Elsevier Inc.

关键词： Common voting rules Three-way decisions Weighted partial orders

来源：评论

学校读者我要写书评

暂无评论

Discriminative Additive Scale Loss for Deep Imbalanced Classification and Embedding

Discriminative Additive Scale Loss for Deep Imbalanced Class...

引用

IEEE International Conference on data Mining (ICDM)

作者： Zhao Zhang Weiming Jiang Yang Wang Qiaolin Ye Mingbo Zhao Mingliang Xu Meng Wang School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China AI team Shanghai Shizhuang Information Technology Co. Ltd Shanghai China College of Information Science and Technology Nanjing Forestry University Nanjing China School of Information Science and Technology Donghua University Shanghai China School of Information Engineering Zhengzhou University Zhengzhou China

ISBN: (纸本)9781665423991

Real-world data in emerging applications may suffer from highly-skewed class imbalanced distribution, however how to deal with this kind of problem appropriately through deep learning needs further investigation. In this paper, we mainly propose a novel cross-entropy based loss function, referred to as Additive Scale Loss (ASL), for deep representation learning and imbalanced classification. To deal with the class imbalanced problem, ASL aims at increasing the loss in case of misclassification, which can avoid the superimposed loss values caused by the large amount of easily classified data in the unbalanced database to dominate the loss value of misclassified data. Moreover, in real-world applications, one data source may be used for multiple scenarios, such as classification and embedding learning, however training two separable models to handle these problems is costly, especially in deep learning area. To tackle this issue, we present and integrate a discriminative inter-class separation term into ASL, and propose a discriminative ASL (D-ASL), which can not only improve the classification performance, but also obtain discriminative representations simultaneously. The discriminative inter-class separation term is general, and can be easily integrated to other loss functions, such as CE and FL, as the byproducts. Finally, a new deep convolutional neural network equipped with D-ASL and a fully-connected (FC) layer is proposed, which can classify the imbalanced image data and obtain the discriminative representations at the same time. Extensive experimental results verified the superior performance of our method.

关键词： Deep learning Training Representation learning Additives databases Soft sensors Conferences

来源：评论

学校读者我要写书评

暂无评论

Unsupervised vehicle re-identification with progressive adaptation

arXiv

引用

arXiv 2020年

作者： Peng, Jinjia Wang, Yang Wang, Huibing Zhang, Zhao Fu, Xianping Wang, Meng College of Information and Science Technology Dalian Maritime University LiaoningDalian China Pengcheng Laboratory ShenzhenGuangdong China Key Laboratory of Knowledge Engineering with Big Data Ministry of education Hefei University of Technology China School of Computer Science and Information Engineering Hefei University of Technology China

Vehicle re-identification (reID) aims at identifying vehicles across different non-overlapping cameras views. The existing methods heavily relied on well-labeled datasets for ideal performance, which inevitably causes fateful drop due to the severe domain bias between the training domain and the real-world scenes;worse still, these approaches required full annotations, which is labor-consuming. To tackle these challenges, we propose a novel progressive adaptation learning method for vehicle reID, named PAL, which infers from the abundant data without annotations. For PAL, a data adaptation module is employed for source domain, which generates the images with similar data distribution to unlabeled target domain as "pseudo target samples". These pseudo samples are combined with the unlabeled samples that are selected by a dynamic sampling strategy to make training faster. We further proposed a weighted label smoothing (WLS) loss, which considers the similarity between samples with different clusters to balance the confidence of pseudo labels. Comprehensive experimental results validate the advantages of PAL on both VehicleID and VeRi-776 dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Triplet Deep Subspace Clustering via Self-Supervised data Augmentation

Triplet Deep Subspace Clustering via Self-Supervised Data Au...

引用

IEEE International Conference on data Mining (ICDM)

作者： Zhao Zhang Xianzhen Li Haijun Zhang Yi Yang Shuicheng Yan Meng Wang School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China School of Computer Science and Technology Soochow University Suzhou China Harbin Institute of Technology (Shenzhen) Shenzhen China Centre for Artificial Intelligence University of Technology Sydney Sydney NSW Australia Sea AI Lab (SAIL) & National University of Singapore Singapore

ISBN: (纸本)9781665423991

Deep subspace clustering (DSC) with the auto-encoder and self-expression layer is of great concern due to encouraging performance. However, existing methods usually adopt a “single-task” strategy based on a single dataset, without considering other related tasks or data. As such, they cannot discover other useful information to improve the clustering task. Besides, the local structure preservation of the latent codes in mapping is usually ignored. In this paper, we therefore present an effective “multi-task” strategy via the self-supervised data augmentation, and propose a new end-to-end trainable Triplet Deep Subspace Clustering Network (TDSC-net). Specifically, TDSC-net firstly generates triplet data (i.e., anchor, positive and negative data) from input data by a spectral clustering module and a self-supervised data augmentation module. This can enable it to inherit the merits of self-supervised learning and multitask learning implicitly. After that, TDSC-net builds a triplet deep autoencoder network with a self-expression layer, which takes the triplet data as input, where they share the common network layers (i.e., autoencoder and self-expression layers) over the triple tasks for complementary learning and mutual supervision. A triplet loss is also included to retain the local information of deep latent codes, which will also benefit the self-expression. Furthermore, TDSC-net separates the self-expression layer from decoding process to improve the efficiency of reconstruction. Extensive results on several public datasets demonstrate the effectiveness of our triplet-task DSC strategy.

关键词： Codes Conferences Multitasking Decoding data mining Task analysis

来源：评论

学校读者我要写书评

暂无评论

Retracted: Measurement and analysis of Chinese journal discriminative capacity

引用

Journal of Informetrics 2021年第1期15卷

作者： Baolong Zhang Hao Wang Sanhong Deng Xinning Su School of Information Management Nanjing University Nanjing 210023 China Jiangsu Key Laboratory of Data Engineering and Knowledge Service Nanjing 210023 China

来源：评论

学校读者我要写书评

暂无评论

Finedge: A Dynamic Cost-Efficient Edge Resource Management Platform for NFV Network

Finedge: A Dynamic Cost-Efficient Edge Resource Management P...

引用

International Workshop on Quality of Service

作者： Miao Li Qixia Zhang Fangming Liu 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 China

ISBN: (数字)9781728168876

ISBN: (纸本)9781728168883

With the evolution of network function virtualization (NFV) and edge computing, software-based network functions (NFs) can be deployed on closer-to-end-user edge servers to support a broad range of new services with high bandwidth and low latency. However, due to the resource limitation, strict QoS requirements and real-time flow fluctuations in edge network, existing cloud-based resource management strategy in NFV platforms is inefficient to be applied to the edge. Thus, we propose Finedge, a dynamic, fine-grained and cost-efficient edge resource management platform for NFV network. First, we conduct empirical experiments to find out the effect of NFs' resource allocation and their flow-level characteristics on performance. Then, by jointly considering these factors and QoS requirements (e.g., latency and packet loss rate), Finedge can automatically assign the most suitable CPU core and tune the most cost-efficient CPU quota to each NF. Finedge is also implemented with some key strategies including real-time flow monitoring, elastic resource scaling up and down, and also flexible NF migration among cores. Through extensive evaluations, we validate that Finedge can efficiently handle heterogeneous flows with the lowest CPU quota and the highest SLA satisfaction rate as compared with the default OS scheduler and other state-of-the-art resource management schemes.

关键词： Resource management Noise measurement Packet loss Servers Throughput Quality of service

来源：评论

学校读者我要写书评

暂无评论

Heat to Power: Thermal Energy Harvesting and Recycling for Warm Water-Cooled datacenters

Heat to Power: Thermal Energy Harvesting and Recycling for W...

引用

Annual International Symposium on Computer Architecture, ISCA

作者： Xinhui Zhu Weixiang Jiang Fangming Liu Qixia Zhang Li Pan Qiong Chen Ziyang Jia 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 China

ISBN: (数字)9781728146614

ISBN: (纸本)9781728146621

Warm water cooling has been regarded as a promising method to improve the energy efficiency of water-cooled datacenters. In warm water-cooling systems, hot spots occur as a common problem where the hybrid cooling architecture integrating thermoelectric coolers (TECs) emerges as a new remedy. Equipped with this architecture, the inlet water temperature can be raised higher, which provides more opportunities for heat recycling. However, currently, the heat absorbed from the server components is ejected directly into the water without being recycled, which leads to energy wasting. In order to further improve the energy efficiency, we propose Heat to Power (H2P), an economical and energy-recycling warm water cooling architecture, where thermoelectric generators (TEGs) harvest thermal energy from the “used” warm water and generate electricity for reusing in datacenters. Specifically, we propose some efficient optimization methods, including an economical water circulation design, fine-grained adjustments of the cooling setting and dynamic workload scheduling for increasing the power generated by TEGs. We evaluate H2P based on a real hardware prototype and cluster traces from Google and Alibaba. Experiment results show that TEGs equipped with our optimization methods can averagely generate 4.349 W, 4.203 W, and 3.979 W (4.177 W averagely) electricity on one CPU under the drastic, irregular and common workload traces, respectively. The power reusing efficiency (PRE) can reach 12.8%~16.2% (14.23% averagely) and the total cost of ownership (TCO) of datacenters can be reduced by up to 0.57%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

knowledge graph enhanced neural collaborative recommendation

引用

Expert Systems with Applications 2021年 164卷 113992-113992页

作者： Sang, Lei Xu, Min Qian, Shengsheng Wu, Xindong Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology) Ministry of Education Hefei 230009 China Faculty of Engineering and Information Technology University of Technology Sydney Sydney 2007 Australia School of Computer Science and Information Engineering Hefei University of Technology Hefei 230009 China Institute of Automation Chinese Academy of Sciences Beijing 100190 China Mininglamp Academy of Sciences Mininglamp Technology Beijing 100084 China

Existing neural collaborative filtering (NCF) recommendation methods suffer from severe sparsity problem. knowledge Graph (KG), which commonly consists of fruitful connected facts about items, presents an unprecedented opportunity to alleviate the sparsity problem. However, pure NCF models can hardly model the high-order connectivity in KG, and ignores complex pairwise correlations between user/item embedding dimensions. To address these problems, we propose a novel knowledge graph enhanced Neural Collaborative Recommendation (K-NCR) framework, which effectively combines user–item interaction information and auxiliary knowledge information for recommendation task into three parts: (1) For items, the proposed propagating model learns the representation of item entity. It recursively aggregates information from its multi-hop neighbours in KG, and employs an attention mechanism to discriminate the importance of the relation type to mine users’ potential preferences. (2) For users, another heterogeneous attention weights are leveraged to strengthen the embedding learning of users. (3) The user and item embeddings are then fed into a newly designed two-dimensional interaction map with convolutional hidden layers to model the complex pairwise correlations between their embedding dimensions explicitly. Extensive experimental results on three benchmark datasets demonstrate the effectiveness of our K-NCR framework. © 2020

关键词： Attention mechanism Graph convolutional networks knowledge graph Neural collaborative filtering Recommendation system

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：