检索结果-内蒙古大学图书馆

IEEE International Conference on Cloud Computing and big data Analysis (ICCCBDA)

作者： Wei Zhang Xiaofei Liao Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781728160245

ISBN: (纸本)9781728160252

FPGA has been considered as a promising solution to accelerate Convolutional Neural Networks (CNNs) for its excellent performance in energy efficiency and programmability. However, prior designs are usually designed for inference only as designers can map pre-trained models to the hardware in a very efficient way. However, those approaches may not be suitable for training CNN models. In this paper, we propose FConv, in which the CPU and FPGA work together in a fine-grained manner. The FPGA accelerator in FConv uses one Winograd-based convolver, which reduces the design complexity and improves performance. We apply double-buffer for output routine to effectively overlap computation and data transfer. We also integrate multiple PEs to improve data parallelism. We propose our analytical model for prediction and use it as a guide in task scheduling. We find the upper limit of performance under the current design based on the analytical model. We evaluate our design on VGG-16 and Densnet-40 on ImageNet and CIFAR-10. We achieve 262.43 GOP/s on the VGG-16 model, which is 2.13× of the performance compared to FFT-based implementation on the same platform. We also achieve at most 4×+ performance improvement compared MKL with 20 threads running on 10 core Intel processors.

关键词： Field programmable gate arrays Computational modeling Training Convolution Acceleration Bandwidth Task analysis

来源：评论

学校读者我要写书评

暂无评论

Context-Aware Feature Attention Model for Coreference Resolution on Biomedical Texts

Research Square

引用

Research Square 2021年

作者： Li, Yufei Zhou, Xiangyu Ma, Jie Ma, Xiaoyong Li, Chen School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an China National Engineering Lab for Big Data Analytics Xi’an Jiaotong University Shaanxi Xi’an China Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Technology Research and Development Xi’an Jiaotong University Shaanxi Xi’an China

Background: Bio-entity Coreference resolution is an important task to gain a complete understanding of biomedical texts automatically. Previous neural network-based studies on this topic are domain system based methods which rely on some domain-specific information integration. However, for the identical mentions, this may lead to misleading information, as the model tends to get similar or even identical representations, which further leads to wrongful predictions. Results: we propose a new context-aware Feature Attention model to distinguish identical mentions effectively to better resolve coreference. The new model can represent identical mentions based on different contexts by adaptively exploiting features effectively. The proposed model substantially outperforms the state-of-the-art baselines on the BioNLP dataset with a 64.0% F1 score and further demonstrates superior performance on the differential representation and coreferential link of identical mentions. Conclusion: The context-aware Feature Attention model adaptively exploit features and represent identical mentions according to different contexts, which significantly makes the system obtain semantic information effectively and make more accurate predictions. Considering that this approach is still limited when context information is insufficient, we expect to utilize such information more fine-grained with the help of the external knowledge base in coreference resolution. © 2021, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Optimal Margin Distribution Machine with Sparsity Inducing Penalty

Optimal Margin Distribution Machine with Sparsity Inducing P...

引用

International Conference on big data and Smart Computing (bigCOMP)

作者： Teng Zhang Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781728160344

ISBN: (纸本)9781728160351

Recently a promising research direction of statistical learning has been advocated, i.e., the optimal margin distribution learning, with the central idea of optimizing the margin distribution. As the most representative approach of this new learning paradigm, the optimal margin distribution machine (ODM) considers maximizing the margin mean and minimizing the margin variance simultaneously. The standard ODM exploits the ℓ_2-norm penalty, which gives rise to a dense decision boundary. However, in some situations, the model with parsimonious representation is more preferred, due to the redundant noisy features or limited computing resources. In this paper, we propose the sparse optimal margin distribution machine (Sparse ODM), which aims to achieve better generalization performance with moderate model size. For optimization, we extends an efficient coordinate descent method to solve the final problem since the variables are decoupled. In each iteration, we propose a modified Newton method to solve the one-variable sub-problem. Experimental results on both synthetic and real data sets show the superiority of the proposed method.

关键词： Standards Newton method Noise measurement Optimization Support vector machines Computational modeling Training

来源：评论

学校读者我要写书评

暂无评论

Learning to Reweight Samples with Offline Loss Sequence

Learning to Reweight Samples with Offline Loss Sequence

引用

IEEE International Conference on data Mining (ICDM)

作者： Yuhua Wei Xiaoyu Li Jishang Wei Buyue Qian Chen Li School of Computer Science and Technology Xi’an Jiaotong University Xi’an China HP Labs 1501 Page Mill Rd Palo Alto CA USA The First Affiliated Hospital of Xi’an Jiaotong University Xi’an China National Engineering Lab for Big Data Analytics Xi’an Jiaotong University Xi’an China

ISBN: (纸本)9781665423991

Deep neural networks (DNNs) provide the best of class solutions to many supervised tasks due to their powerful function fitting capabilities. However, it is challenging to handle data bias, such as label noise and class imbalance, when applying DNNs to solve real-world problems. Sample reweighting is a popular strategy to tackle data bias, which assigns higher weights to informative samples or samples with clean labels. However, conventional reweighting methods require prior knowledge of the distribution information of data bias, which is intractable in practice. In recent years, meta-learning-based methods have been proposed to learn to assign weights to training samples adaptively by using their online training loss or gradient directions. However, the latent bias distribution cannot be adequately characterized in an online fashion. The online loss distribution changes over the training procedure, making it even harder to perform the sample weight learning. In contrast to past methods, we propose a two-stage training strategy to tackle the above problems. In the first stage, the loss sequences of samples are collected. In the second stage, a subnet with convolutional layers is utilized to learn the mapping from offline sample loss sequence to sample weight adaptively. Guided by a small unbiased meta dataset, this subnet is optimized iteratively with the main classifier network in a meta-learning manner. Empirical results show that our method, called Meta Reweighting with Offline Loss Sequence (MROLS), outperforms state-of-the-art reweighting techniques on most benchmarks. Moreover, the weights of training samples learned via MROLS can be well utilized by other classifiers, which can directly enhance the standard training schema. Our source code is available at https://***/Neronjust2017/MROLS.

关键词： Training Convolutional codes Deep learning Conferences Neural networks Fitting Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Invisible backdoor attack with sample-specific triggers

arXiv

引用

arXiv 2020年

作者： Li, Yuezun Li, Yiming Wu, Baoyuan Li, Longkang He, Ran Lyu, Siwei Ocean University of China Qingdao China School of Data Science The Chinese University of Hong Kong Shenzhen China Secure Computing Lab of Big Data Shenzhen Research Institute of Big Data Shenzhen China Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China NLPR/CRIPAC Institute of Automation Chinese Academy of Sciences Beijing China University at Buffalo SUNY NY United States

Recently, backdoor attacks pose a new security threat to the training process of deep neural networks (DNNs). Attackers intend to inject hidden backdoors into DNNs, such that the attacked model performs well on benign samples, whereas its prediction will be maliciously changed if hidden backdoors are activated by the attacker-defined trigger. Existing backdoor attacks usually adopt the setting that triggers are sample-agnostic, i.e., different poisoned samples contain the same trigger, resulting in that the attacks could be easily mitigated by current backdoor defenses. In this work, we explore a novel attack paradigm, where backdoor triggers are sample-specific. In our attack, we only need to modify certain training samples with invisible perturbation, while not need to manipulate other training components (e.g., training loss, and model structure) as required in many existing attacks. Specifically, inspired by the recent advance in DNN-based image steganography, we generate sample-specific invisible additive noises as backdoor triggers by encoding an attacker-specified string into benign images through an encoder-decoder network. The mapping from the string to the target label will be generated when DNNs are trained on the poisoned dataset. Extensive experiments on benchmark datasets verify the effectiveness of our method in attacking models with or without defenses. The code will be available at https://***/yuezunli/ISSBA. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Heterogeneous PIM Hardware-Software Co-Design for Energy-Efficient Graph Processing

A Heterogeneous PIM Hardware-Software Co-Design for Energy-E...

引用

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Yu Huang Long Zheng Pengcheng Yao Jieshan Zhao Xiaofei Liao Hai Jin Jingling Xue National Engineering Research Center for Big Data Technology and System/Service Computing Technology and System Lab/Cluster and Grid Computing Lab Huazhong University of Science and Technology China UNSW Sydney Australia

ISBN: (数字)9781728168760

ISBN: (纸本)9781728168777

Processing-In-Memory (PIM) is an emerging technology that addresses the memory bottleneck of graph processing. In general, analog memristor-based PIM promises high parallelism provided that the underlying matrix-structured crossbar can be fully utilized while digital CMOS-based PIM has a faster single-edge execution but its parallelism can be low. In this paper, we observe that there is no absolute winner between these two representative PIM technologies for graph applications, which often exhibit irregular workloads. To reap the best of both worlds, we introduce a new heterogeneous PIM hardware, called Hetraph, to facilitate energy-efficient graph processing. Hetraph incorporates memristor-based analog computation units (for high-parallelism computing) and CMOS-based digital computation cores (for efficient computing) on the same logic layer of a 3D die-stacked memory device. To maximize the hardware utilization, our software design offers a hardware heterogeneity-aware execution model and a workload offloading mechanism. For performance speedups, such a hardware-software co-design outperforms the state-of-the-art by 7.54 ×(CPU), 1.56 ×(GPU), 4.13× (memristor-based PIM) and 3.05× (CMOS-based PIM), on average. For energy savings, Hetraph reduces the energy consumption by 57.58× (CPU), 19.93× (GPU), 14.02 ×(memristor-based PIM) and 10.48 ×(CMOS-based PIM), on average.

关键词： Hardware Computer architecture Parallel processing Three-dimensional displays Computational modeling Graphics processing units Memristors

来源：评论

学校读者我要写书评

暂无评论

High Performance DDoS Attack Detection System Based on Distribution Statistics 16th

High Performance DDoS Attack Detection System Based on Distr...

引用

16th IFIP WG 10.3 International Conference on Network and Parallel Computing, NPC 2019

作者： Xie, Xia Li, Jinpeng Hu, Xiaoyang Jin, Hai Chen, Hanhua Ma, Xiaojing Huang, Hong National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9783030307080

Nowadays, web servers often face the threat of distributed denial of service attacks and their intrusion prevention systems cannot detect those attacks effectively. Many existing intrusion prevention systems detect attacks by the state of per-flow and current processing speed cannot fulfill the requirements of real-time detection due to the high speed traffic. In this paper, we propose a powerful system TreeSketchShield which can improve sketch data structure and detect attacks quickly. First, we discuss a novel structure TreeSketch to obtain statistics of network flow, which utilizes the stepped structure of binary tree to map the distribution and reduces the complexity of the statistic calculation. Second, we present a two-level detection scheme that could make a compromise between the detection speed and detection accuracy. Experimental results show that our method can process more than 100,000 records per second. The false alarm rate can achieve 2% to 25% performance improvement. © 2019, IFIP International Federation for Information Processing.

关键词： Binary trees

来源：评论

学校读者我要写书评

暂无评论

Temporal Output Discrepancy for Loss Estimation-Based Active Learning

arXiv

引用

arXiv 2022年

作者： Huang, Siyu Wang, Tianyang Xiong, Haoyi Wen, Bihan Huan, Jun Dou, Dejing The Harvard John A. Paulson School of Engineering and Applied Sciences Harvard University CambridgeMA02134 United States The Department of Computer Science and Information Technology Austin Peay State University ClarksvilleTN37044 United States The Big Data Laboratory Baidu Research Beijing100193 China The School of Electrical and Electronic Engineering Nanyang Technological University Singapore639798 Singapore The AWS AI Lab Amazon SeattleWA98109 United States

While deep learning succeeds in a wide range of tasks, it highly depends on the massive collection of annotated data which is expensive and time-consuming. To lower the cost of data annotation, active learning has been proposed to interactively query an oracle to annotate a small proportion of informative samples in an unlabeled dataset. Inspired by the fact that the samples with higher loss are usually more informative to the model than the samples with lower loss, in this article we present a novel deep active learning approach that queries the oracle for data annotation when the unlabeled sample is believed to incorporate high loss. The core of our approach is a measurement temporal output discrepancy (TOD) that estimates the sample loss by evaluating the discrepancy of outputs given by models at different optimization steps. Our theoretical investigation shows that TOD lower-bounds the accumulated sample loss thus it can be used to select informative unlabeled samples. On basis of TOD, we further develop an effective unlabeled data sampling strategy as well as an unsupervised learning criterion for active learning. Due to the simplicity of TOD, our methods are efficient, flexible, and task-agnostic. Extensive experimental results demonstrate that our approach achieves superior performances than the state-of-the-art active learning methods on image classification and semantic segmentation tasks. In addition, we show that TOD can be utilized to select the best model of potentially the highest testing accuracy from a pool of candidate models. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of time irreversibility and amplitude irreversibility based on joint permutation

arXiv

引用

arXiv 2022年

作者： Yao, Wenpo Yao, Wenli Xu, Rongshuang Wang, Jun School of Geographic and Biologic Information Smart Health Big Data Analysis and Location Services Engineering Lab of Jiangsu Province Nanjing University of Posts and Telecommunications Nanjing210023 China Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Fudan University Ministry of Education China Department of Hydraulic Engineering School of Civil Engineering Tsinghua University Beijing100084 China School of Applied Meteorology Nanjing University of Information Science & Technology Nanjing210044 China

Although time irreversibility (TIR) and amplitude irreversibility (AIR) are relevant concepts for nonequilibrium analysis, their association has received little attention. This paper conducts a systematic comparative analysis of the relationship between TIR and AIR based on statistical descriptions and numerical simulations. To simplify the quantification of TIR and AIR, the amplitude permutation and global information of the associated vector are combined to produce a joint probability estimation. Chaotic logistic, Henon, and Lorenz series are generated to evaluate TIR and AIR according to surrogate theory, and the distributions of joint permutations for these model series are measured to compare the degree of TIR and AIR. The joint permutation TIR and AIR are then used to investigate nonequilibrium pathological features in epileptic electroencephalography data. Test results suggest that epileptic brain electrical activities, particular those during the onset of seizure, manifest higher nonequilibrium characteristics. According to the statistical definitions and targeted pairs of joint permutations in the chaotic model data, TIR and AIR are fundamentally different nonequilibrium descriptors from time- and amplitude-reversibility, respectively, and thus require different forms of numerical analysis. At the same time, TIR and AIR both provide measures for fluctuation theorems associated with nonequilibrium processes, and have similar probabilistic differences in the pairs of joint permutations and consistent outcomes when used to analyze both the model series and real-world signals. Overall, comparative analysis of TIR and AIR contributes to our understanding of nonequilibrium features and broadens the scope of quantitative nonequilibrium measures. Additionally, the construction of joint permutations contributes to the development of symbolic time series analysis. Copyright © 2022, The Authors. All rights reserved.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Failure order: A missing piece in disk failure processing of data centers 21

Failure order: A missing piece in disk failure processing of...

引用

21st IEEE International Conference on High Performance Computing and Communications, 17th IEEE International Conference on Smart City and 5th IEEE International Conference on data science and Systems, HPCC/SmartCity/DSS 2019

作者： Yi, Yusheng Xiao, Jiang Wu, Song Li, Huichuwu Jin, Hai National Engineering Research Center for Big Data Technology System Services Computing Technology System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781728120584

To avoid data loss, data centers adopt disk failure prediction (DFP) technology to raise warnings ahead of actual disk failures, and process the warnings in the order they are raised, i.e., a first-in-first-out (FIFO) warning order. The FIFO-guided warning order can process warnings timely when disk failures are rare in data centers. With the growing scale of data centers, the increasing number of disk failures leads to a complex situation that multiple warnings are raised simultaneously, where the FIFO-guided warning order neither processes warnings timely, nor manages warnings properly due to lack of the priority of warnings. Thus, a real-time and finer-grained priority guidance for warning order management is an urgent need. To this end, we turn our attention to the failures since each warning corresponds to a fail event. The key insight is that the interdependence of failures, i.e., the order failure occurred, indicates the order of warning processing. With an accurate failure order, data centers can decrease the probability of data loss and the downtime of latency-sensitive applications by processing urgent warnings in advance. In this paper, we predict the failure order with a LambdaMART model, which is a state-of-the-art ranking algorithm in information retrieval. To avoid overly concerning on the correctness of high-rank warnings in information retrieval, we design a symmetric metric to evaluate the prediction evaluation of failure order. Experiment on a public dataset, provided by the Backblaze company, shows that our model outperforms the FIFO order and the order from previous DFP models. © 2019 IEEE.

关键词： Information retrieval

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：