检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Yang, Yuting Huang, Pei Cao, Juan Li, Jintao Lin, Yun Dong, Jin Song Ma, Feifei Zhang, Jian Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Beijing China National University of Singapore Singapore Laboratory of Parallel Software and Computational Science ISCAS Beijing China

Recent years have seen the wide application of NLP models in crucial areas such as finance, medical treatment, and news media, raising concerns of the model robustness and vulnerabilities. In this paper, we propose a novel prompt-based adversarial attack to compromise NLP models and robustness enhancement technique. We first construct malicious prompts for each instance and generate adversarial examples via mask-and-filling under the effect of a malicious purpose. Our attack technique targets the inherent vulnerabilities of NLP models, allowing us to generate samples even without interacting with the victim NLP model, as long as it is based on pre-trained language models (PLMs). Furthermore, we design a prompt-based adversarial training method to improve the robustness of PLMs. As our training method does not actually generate adversarial samples, it can be applied to large-scale training sets efficiently. The experimental results show that our attack method can achieve a high attack success rate with more diverse, fluent and natural adversarial examples. In addition, our robustness enhancement method can significantly improve the robustness of models to resist adversarial attacks. Our work indicates that prompting paradigm has great potential in probing some fundamental flaws of PLMs and fine-tuning them for downstream tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

LTKT: Knowledge Tracing Based on Positive and Negative Learning Transfers

SSRN

引用

SSRN 2023年

作者： Xu, Jia Tang, Rongrong Lv, Pin Yu, Minghe Yu, Ge Chen, Enhong School of Computer Electronics and Information Guangxi University GuangXi Nanning530004 China Key Laboratory of Parallel Distributed and Intelligent Computing Education Department of Guangxi Zhuang Autonomous Region Guangxi530004 China Northeastern University Shenyang110819 China University of Science and Technology of China Hefei230088 China

Knowledge Tracing (KT) is a critical but challenging problem for many educational applications. As an essential part of educational psychology, the propagated influence among pedagogical concepts (i.e., learning transfer) is important for optimizing KT tasks. However, existing KT methods only consider the positive learning transfer and neglect the negative learning transfer. To this end, in this paper, we propose a novel deep knowledge tracing model, called positive and negative Learning Transfers based Knowledge Tracing (LTKT). To the best of our knowledge, LTKT makes the first attempt to concurrently utilize the positive and negative learning transfer relations among concepts to improve KT results. First, LTKT employs a statistical-based approach to construct a learning transfer graph (LTG). Then, LTKT quantifies the impact of an exercise's practice result on the knowledge state of the concept via a direct learning effect component, after which a learning transfer effect component is carefully designed to quantify the impact of the practice result on the knowledge states of neighboring concepts based on the positive and negative learning transfer relations modeled by LTG. We conduct extensive experiments on public real-world datasets, and the experimental results show that LTKT outperforms all state-of-the-art KT methods and has good interpretability. © 2023, 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

Simulation of Nuclear Reactor Accident Scenarios using Physics-Informed Neural Networks and Transfer-Learning

Simulation of Nuclear Reactor Accident Scenarios using Physi...

引用

Electronic Information Engineering and Computer science (EIECS), 2021 International Conference on

作者： Yang Yu Yufei Xie Wenlin Wang Guohua Wu Haitao Lan Enbo Lin Ping An Zibin Sun Haichuan Zhang Yixian Wu National Key Laboratory of Parallel and Distributed Computing National University of Defense Technology Changsha China Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu China School of Automation Wuhan University of Technology Wuhan China Sino-German College of Intelligent Manufacturing Shenzhen Technology University Shenzhen China Institute of Automotive Engineers Hubei University of Automotive Technology Shiyan China Nuclear Power Institute of China Chengdu China

ISBN: (数字)9798331531409

ISBN: (纸本)9798331531416

In a Loss of Coolant Accident (LOCA), reactor core temperatures can rise rapidly, leading to potential fuel damage and radioactive material release. This research presents a groundbreaking method that combines the power of Monte Carlo Sampling and Physics-Informed Neural Networks (PINNs) to simulate and effectively address the challenging Loss of Coolant Accidents (LOCA) in nuclear reactors. In the event of a LOCA, reactor core temperatures can soar rapidly, posing a significant threat to fuel integrity and potentially leading to the release of radioactive materials. By leveraging the strengths of both Monte Carlo Sampling and PINNs, this approach aims to provide a comprehensive and accurate simulation framework for assessing and mitigating the consequences of such accidents. The method yields high prediction accuracy (MAE: 0.033, RMSE: 0.098, R2: 0.814) and demonstrates robustness through transfer learning, maintaining strong performance (MAE: 0.064, RMSE: 0.163, R 2 : 0.735).

关键词： Radioactive materials Accuracy Monte Carlo methods Transfer learning Neural networks Robustness Data models Fuels Inductors Accidents

来源：评论

学校读者我要写书评

暂无评论

Accelerating MatLab code using GPU: A review of tools and strategies

Accelerating MatLab code using GPU: A review of tools and st...

引用

International Conference on Artificial Intelligence, Management science and Electronic Commerce (AIMSEC)

作者： Baida Zhang Shuai Xu Feng Zhang Yuan Bi Linqi Huang National laboratory for Parallel and Distributed Processing School of Computer National University of Defense Technology Changsha China Department of Information Engineering Academy of Armored Forces Engineering Beijing China Inspur (Beijing) Electronic Information Industry Company Limited Beijing China Naval Academy of Armament Beijing China School of Resources and Safety Engineering Central South University Changsha China

Lots of toolboxes of accelerating MatLab using GPU are available now[1], but, users are confused by which toolbox is best suitable for a particular task. Three toolboxes-Jacket, GPUmat, and parallel Computing Toolbox of MatLab are selected. For each toolbox, its advantages and pitfalls are reviewed, with an aim to allow the reader to identify which toolbox is appropriate for a given task. Strategies of whether a function should execute on GPU are given after a formula analysis. The analysis is also a framework for program automatically decides which function is cost-efficient to execute on GPU. A series of benchmark of different types of computing, including data transfer between GPU and CPU, data matrix Generation, matrix operation and GPU functions were tested in all three toolboxes. And the results show that Jacket is the best one. Some advices to improve the performance of toolboxes are given in the end.

关键词： Graphics processing unit Acceleration parallel processing Computer architecture Conferences Licenses MATLAB

来源：评论

学校读者我要写书评

暂无评论

Quantifying robustness to adversarial word substitutions

arXiv

引用

arXiv 2022年

作者： Yang, Yuting Huang, Pei Ma, Fei Fei Cao, Juan Zhang, Meishan Zhang, Jian Li, Jintao Key Lab Of Intelligent Information Processing Institute Of Computing Technology Chinese Academy Of Sciences Beijing100190 China University Of Chinese Academy Of Sciences Beijing100049 China Beijing100190 China Laboratory Of Parallel Software And Computational Science ISCAS Beijing100190 China China

Deep-learning-based NLP models are found to be vulnerable to word substitution perturbations. Before they are widely adopted, the fundamental issues of robustness need to be addressed. Along this line, we propose a formal framework to evaluate word-level robustness. First, to study safe regions for a model, we introduce robustness radius which is the boundary where the model can resist any perturbation. As calculating the maximum robustness radius is computationally hard, we estimate its upper and lower bound. We repurpose attack methods as ways of seeking upper bound and design a pseudo-dynamic programming algorithm for a tighter upper bound. Then verification method is utilized for a lower bound. Further, for evaluating the robustness of regions outside a safe radius, we reexamine robustness from another view: quantification. A robustness metric with a rigorous statistical guarantee is introduced to measure the quantification of adversarial examples, which indicates the model's susceptibility to perturbations outside the safe radius. The metric helps us figure out why state-of-the-art models like BERT can be easily fooled by a few word substitutions, but generalize well in the presence of real-world noises. Copyright © 2022, The Authors. All rights reserved.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Structure and method for hardware acceleration of variable data set management

引用

Hunan Daxue Xuebao/Journal of Hunan University Natural sciences 2013年第11 SUPPL.期40卷 68-73页

作者： Xu, Jin-Bo Dou, Yong Sun, Cai-Xia Dong, Ya-Zhuo Wang, Shao-Gang Lu, Ping-Jing Zhang, Jun College of Computer National Univ of Defense Technology Changsha Hunan 410073 China National Laboratory for Parallel and Distributed Processing National Univ of Defense Technology Changsha Hunan 410073 China Unit 91655 People's Liberation Army Beijing 100036 China

A general hardware structure was proposed to accelerate variable data set management, which was designed to accept instructions flexibly and accomplish the commonly used functions and some more complicated functions of the linked-list data structure .The structure can access the data based on both pointer and address mechanism. In order to fully utilize the limited memory resources, we proposed a memory recycle scheme to reuse the memory space where the data have been deleted. Experimental results on FPGA show that our proposal can accelerate the variable data set management. Only few hardware resources were used and it consumed pretty low power. Compared with the software linked-list structure in PC, our proposal in FPGA achieved high speedups.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

DrugProtKGE: Weakly Supervised Knowledge Graph Embedding for Highly-Effective Drug-Protein Interaction Representation

DrugProtKGE: Weakly Supervised Knowledge Graph Embedding for...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yanlong Qiu Siqi Wang Xi Yang Xinyuan Qiu Chengkun Wu Yingbo Cui Canqun Yang Institute for Quantum Information & State Key Laboratory of High-Performance Computing College of Computer Science National University of Defense Technology Changsha P. R. China National Supercomputer Center in Tianjin Tianjin P. R. China National Key Laboratory of Parallel and Distributed Computing College of Computer Science National University of Defense Technology Changsha P. R. China Department of Biology and Chemistry College of Science National University of Defense Technology Changsha P. R. China

With the exponential growth of biomedical knowledge in unstructured text repositories such as PubMed, it is imminent to establish a knowledge graph-style, efficient searchable and targeted database that can support the need of information retrieval from researchers and clinicians. To mine knowledge from graph databases, most previous methods view a triple in a graph (see Fig. 1) as the basic processing unit and embed the triplet element (i.e. drugs/chemicals, proteins/genes and their interaction) as separated embedding matrices, which cannot capture the semantic correlation among triple elements. To remedy the loss of semantic correlation caused by disjoint embeddings, we propose a novel approach to learn triple embeddings by combining entities and interactions into a unified representation. Furthermore, traditional methods usually learn triple embeddings from scratch, which cannot take advantage of the rich domain knowledge embedded in pre-trained models, and is also another significant reason for the fact that they cannot distinguish the differences implied by the same entity in the multi-interaction triples. In this paper, we propose a novel fine-tuning based approach to learn better triple embeddings by creating weakly supervised signals from pre-trained knowledge graph embeddings. The method automatically samples triples from knowledge graphs and estimates their pairwise similarity from pre-trained embedding models. The triples are then fed pairwise into a Siamese-like neural architecture, where the triple representation is fine-tuned in the manner bootstrapped by triple similarity scores. Finally, we demonstrate that triple embeddings learned with our method can be readily applied to several downstream applications (e.g. triple classification and triple clustering). We evaluated the proposed method on two open-source drug-protein knowledge graphs constructed from PubMed abstracts, as provided by BioCreative. Our method achieves consistent improvement in both t

关键词：

来源：评论

学校读者我要写书评

暂无评论

Profiling HPC Applications with Low Overhead and High Accuracy

Profiling HPC Applications with Low Overhead and High Accura...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Jingyuan Zhao Xin Liu Yao Liu Penglong Jiao Jinshuo Liu Wei Xue School of Data Science & Engineering East China Normal University Shanghai China School of Cyber Science and Engineering Wuhan University Wuhan China National Research Centre of Parallel Computer Engineering and Technology Beijing China Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai China Tsinghua University Beijing China

As the parallel scale of HPC applications represented by earth system models becomes larger and the computing cost becomes higher, the performance of HPC applications is increasingly critical. Profiling HPC applications accurately helps to model the applications and find the performance bottlenecks. However, due to the complexity of HPC applications, the diversity of programming languages, the differences of individual programming habits, and multiple architectures, accurate profiling becomes very tough. In this paper, we propose LPerf: a low-overhead and high-accuracy profiler for HPC applications. To reduce the profiling overhead and improve the profiling accuracy, we propose a preprocessing method which can automatically instrument with tunable granularity thus significantly reducing the run-time overhead of profiling, an aggregated caller-callee relationship which is used to locate relationship of functions efficiently, and a profiling-aware method which can precisely calculate running time of functions. The experimental results show that the error rate of profiling reaches 0.02%, and the overhead reaches 1.6%, in the earth system model named CAS-ESM. Compared with the baselines, the precision, accuracy, and overhead of LPerf have reached the state of the art.

关键词： Earth Analytical models Schedules Computer languages Costs Error analysis Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Research on Pin-by-Pin Calculation Method of Rectangular Mesh Based on Quasi-Diffusion Theory

SSRN

引用

SSRN 2024年

作者： Zhuang, Kun Yongzhan, Wang Yan, Jiangtao Zou, Hang Deng, Lina Wang, Yingzhen Wang, Sipeng Zhang, Qian Department of Nuclear Science and Technology Nanjing University of Aeronautics and Astronautics Jiangsu Nanjing211106 China China Nuclear Power Operation Technology Corporation LTD. Research Institute of Nuclear Power Operation Hubei Wuhan430223 China Science and Technology on Parallel and Distribution Processing Laboratory National University of Defense Technology Hunan Changsha410073 China Laboratory for Advanced Nuclear Energy Theory and Applications Zhejiang Institute of Modern Physics Department of Physics Zhejiang University Zhejiang Hangzhou310027 China

With the development of nuclear energy techniques, pin-by-pin calculation using the SP3 method based on pin cell homogenization attracts researchers. This study proposed a pin-by-pin calculation method of rectangular mesh based on quasi-diffusion (QD) theory. The QD equation and boundary condition were derived from a transport equation similar to the P1 equation derivation. The Eddington factor was treated as a few-group homogenized parameter and calculated based on a deterministic code ALPHA. The numerical method of QD equation was developed based on nodal expansion method of nonlinear iteration. Some benchmarks were used to verify the Eddington factor and the numerical method of QD. 4 colorset models with different neutron anisotropy levels were analyzed by pin-by-pin-QD method. Pin-by-pin-QD can reduce keff error by about 600 pcm and agree better with reference results. Additionally, it has better accuracy and similar efficiency as diffusion calculation and is suitable for problems with strong anisotropy. © 2024, The Authors. All rights reserved.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Research on accelerating CEE-DGCNN event extraction algorithm based on multi-CPU platform

引用

Journal of Physics: Conference Series 2021年第1期1738卷

作者： Yan Li Jinfei Jiang Jinwei Xu Zikai Gao Yong Dou Haifang Zhou Science and Technology on Parallel and Distributed Laboratory National University of Defense Technology Changsha 410005 China Department of Computational Science National University of Defense Technology Changsha 410005 China

With the development of the Internet, the volume of information is expanding rapidly, and the complex information makes it particularly important to extract information quickly and intelligently. Event extraction algorithm is such a kind of fast and accurate information acquisition algorithm. With the development of deep learning in recent years, deep learning also shines in the field of time extraction. CEE-DGCNN network is an efficient and accurate event extraction algorithm for Chinese text. At present, the acceleration research on deep learning in the academic community mainly focuses on GPU, FPGA and other platforms. In fact, compared with these platforms, CPU is more versatile. Considering that the algorithm should have universality and universality in industrial application, this paper makes an in-depth analysis of CEE-DGCNN algorithm to study its acceleration on CPU. Experiments were carried out on x86 and ARM architectures respectively, and good acceleration effects were achieved.

关键词：

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：