检索结果-内蒙古大学图书馆

Customizing a teacher for feature distillation

INFORMATION SCIENCES 2023年第1期640卷

作者： Tan, Chao Liu, Jie Natl Univ Def Technol Sci & Parallel & Distributed Proc Lab Changsha 410073 Peoples R China Natl Univ Def Technol Lab Software Engn Complex Syst Changsha 410073 Peoples R China

Knowledge distillation is a method to train a lightweight network by transferring class probability knowledge from a cumbersome teacher network. However, transferring only the class probability knowledge would limit the distillation performance. Therefore, several approaches have been proposed to transfer the teacher's knowledge at the feature map level. In this paper, we revisit the feature distillation method and have found that the larger the teacher's architecture/capacity becomes, the more difficult it is for the student to imitate. Thus, the feature distillation method is unable to achieve its full potential. To address this, a novel end-to-end distillation framework, termed Customizing a Teacher for Feature Distillation (CTFD), is proposed to train a teacher to be more compatible with its student. In addition, we apply the customized teacher to three feature distillation methods. Moreover, data augmentation is used as a trick to train the student to improve its generalization performance. Extensive empirical experiments and analyses are conducted on three computer vision tasks, including image classification, transfer learning, and object detection, to substantiate the effectiveness of the proposed method.

关键词： Neural network compression Knowledge distillation Knowledge transfer

来源：评论

学校读者我要写书评

暂无评论

IS-MVSNet:Importance Sampling-Based MVSNet 17th

IS-MVSNet:Importance Sampling-Based MVSNet

引用

17th European Conference on Computer Vision (ECCV)

作者： Wang, Likang Gong, Yue Ma, Xinjun Wang, Qirui Zhou, Kaixuan Chen, Lei Hong Kong Univ Sci & Technol Dept Comp Sci & Engn Clear Water Bay Hong Kong Peoples R China Huawei Technol Distributed & Parallel Software Lab Shenzhen Peoples R China Huawei Technol Riemann Lab Shenzhen Peoples R China Huawei Technol Fundamental Software Innovat Lab Shenzhen Peoples R China

ISBN: (纸本)9783031198236;9783031198243

This paper presents a novel coarse-to-fine multi-view stereo (MVS) algorithm called importance-sampling-based MVSNet (IS-MVSNet) to address a crucial problem of limited depth resolution adopted by current learning-based MVS methods. We proposed an importance-sampling module for sampling candidate depth, effectively achieving higher depth resolution and yielding better point-cloud results while introducing no additional cost. Furthermore, we proposed an unsupervised error distribution estimation method for adjusting the density variation of the importance-sampling module. Notably, the proposed sampling module does not require any additional training and works reasonably well with the pre-trained weights of the baseline model. Our proposed method leads to up to 20x promotion on the most refined depth resolution, thus significantly benefiting most scenarios and excellently superior on fine details. As a result, IS-MVSNet outperforms all the published papers on TNT's intermediate benchmark with an F-score of 62.82%. Code is available at ***/NoOneUST/IS-MVSNet.

关键词： 3D reconstruction Multi-view stereo Importance sampling

来源：评论

学校读者我要写书评

暂无评论

Harmonizing Efficiency and Practicability: Optimizing Resource Utilization in Serverless Computing with JIAGU

Harmonizing Efficiency and Practicability: Optimizing Resour...

引用

USENIX Annual Technical Conference

作者： Liu, Qingyuan Yang, Yanning Du, Dong Xia, Yubin Zhang, Ping Feng, Jia Larus, James R. Chen, Haibo Shanghai Jiao Tong Univ Inst Parallel & Distributed Syst SEIEE Shanghai Peoples R China Minist Educ Engn Res Ctr Domain specif Operating Syst Beijing Peoples R China Chinese Acad Sci Key Lab Syst Software Beijing Peoples R China Huawei Cloud Shenzhen Peoples R China Ecole Polytech Fed Lausanne Lausanne Switzerland

ISBN: (纸本)9781939133410

Current serverless platforms struggle to optimize resource utilization due to their dynamic and fine-grained nature. Conventional techniques like overcommitment and autoscaling fall short, often sacrificing utilization for practicability or incurring performance trade-offs. Overcommitment requires predicting performance to prevent QoS violation, introducing trade-off between prediction accuracy and overheads. Autoscaling requires scaling instances in response to load fluctuations quickly to reduce resource wastage, but more frequent scaling also leads to more cold start overheads. This paper introduces JIAGU to harmonize efficiency with practicability through two novel techniques. First, pre-decision scheduling achieves accurate prediction while eliminating overheads by decoupling prediction and scheduling. Second, dual-staged scaling achieves frequent adjustment of instances with minimum overhead. We have implemented a prototype and evaluated it using real-world applications and traces from the public cloud platform. Our evaluation shows a 54.8% improvement in deployment density over commercial clouds (with Kubemetes) while maintaining QoS, and 81.0%-93.7% lower scheduling costs and a 57.4%-69.3% reduction in cold start latency compared to existing QoS-aware schedulers.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Accelerating aerodynamic design optimization based on graph convolutional neural network

引用

INTERNATIONAL JOURNAL OF MODERN PHYSICS C 2024年第1期35卷 2450007-2450007页

作者： Li, Tiejun Yan, Junjun Chen, Xinhai Wang, Zhichao Zhang, Qingyang Zhou, Enqiang Gong, Chunye Liu, Jie Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Changsha 410073 Hunan Peoples R China Natl Univ Def Technol Lab Digitizing Software Frontier Equipment Changsha Hunan Peoples R China

Computational fluid dynamics (CFD) plays a critical role in many scientific and engineering applications, with aerodynamic design optimization being a primary area of interest. Recently, there has been much interest in using artificial intelligence approaches to accelerate this process. One promising method is the graph convolutional neural network (GCN), a deep learning method based on artificial neural networks (ANNs). In this paper, we propose a novel GCN-based aerodynamic design optimization acceleration framework, GCN-based aerodynamic design optimization acceleration framework. The framework significantly improves processing efficiency by optimizing data flow and data representation. We also introduce a network model called GCN4CFD that uses the GCF framework to create a compact data representation of the flow field and an encoder-decoder structure to extract features. This approach enables the model to learn underlying physical laws in a space-time efficient manner. We then evaluate the proposed method on an airfoil aerodynamic design optimization task and show that GCN4CFD provides a significant speedup compared to traditional CFD solvers while maintaining accuracy. Our experimental results demonstrate the robustness of the proposed framework and network model, achieving a speedup average of 3.0 x.

关键词： Computational fluid dynamics aerodynamic design optimization deep learning graph convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Development of a general framework of resonance self-shielding treatment for broad-spectrum reactor lattice physics calculation

引用

NUCLEAR ENGINEERING AND TECHNOLOGY 2024年第10期56卷 4335-4354页

作者： Zhang, Jinchao Zhang, Qian Zou, Hang Yu, Jialei Cao, Wei Wu, Shifu Qin, Shuai Zhao, Qiang Gilad, Erez Harbin Engn Univ Fundamental Sci Nucl Safety & Simulat Technol Lab Harbin 150001 Peoples R China Zhejiang Univ Zhejiang Inst Modern Phys Dept Phys Lab Adv Nucl Energy Theory & Applicat Hangzhou 310027 Peoples R China Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Changsha 410073 Peoples R China Natl Univ Def Technol Lab Digitizing Software Frontier Equipment Changsha 410073 Peoples R China Ben Gurion Univ Negev Unit Nucl Engn POB 653 IL-8410501 Beer Sheva Israel

Some core designs integrate high-enriched fuel and moderator materials to enhance neutron utilization. This combination results in a broad spectrum within the system, posing challenges in resonance calculation. This paper introduces a general framework to realize resonance self-shielding treatment in broad-spectrum fuel lattice problems. The framework consists of three components. First, a new energy group structure is devised to support resonance calculation in the entire energy range and capture spectral transition and thermalization effects during eigenvalue calculation. Second, the subgroup method based on narrow approximation is selected as a universal method to perform resonance calculation. Finally, transport equations for each fissionable region are solved for neutron flux to collapse the fission spectrum. The proposed method is verified against fast, intermediate, and thermal spectrum pin cell problems and an assembly problem featuring a fast-thermal coupled spectrum. Numerical results affirm the accuracy of the proposed method in handling these scenarios, with eigenvalue errors below 154 pcm for pin cell problems and 106 pcm for the assembly problem. The verification results revealed that the proposed method enables accurate resonance self-shielding treatment for broad-spectrum problems.

关键词： Broad-spectrum Fission spectrum Group structure Subgroup method

来源：评论

学校读者我要写书评

暂无评论

TeeSwap: Private Data Exchange using Smart Contract and Trusted Execution Environment 23

TeeSwap: Private Data Exchange using Smart Contract and Trus...

引用

23rd IEEE International Conference on High Performance Computing and Communications, 7th IEEE International Conference on Data Science and Systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021

作者： Chen, Peng Shi, Peichang Xu, Jie Fu, Xiang Li, Linhui Zhong, Tao Xiang, Liangliang Kong, Jinzhu College of Computer National University of Defense Technology National Key Laboratory of Parallel and Distributed Processing Changsha410073 China Zhejiang Lab Hangzhou311100 China Kylin Software Co. Ltd Changsha410073 China

ISBN: (纸本)9781665494571

With importance of data value is approved, data-sharing will create more and greater value has become consensus. However, data exchange has to use a trusted third party(TTP) as an intermediary in an untrusted network environment, which may lead to leakage of data privacy. In this paper, we design a system named TeeSwap, which uses smart contract to complete data exchange, and at the same time uses cryptographic algorithms and trusted execution environment (TEE) to ensure privacy in process of data transmission, verification and contract execution. Meanwhile, TeeSwap can ensure the credibility, fairness, integrity and privacy while data are shared in our system. In the end, we implement contracts about data market and data exchange. When confirming the data transaction, data market contract can automatically generate and deploy exchange contract, which can complete the data exchange authoritatively. © 2021 IEEE.

关键词： Data privacy Smart contracts Data communication Cryptography

来源：评论

学校读者我要写书评

暂无评论

A data-free Kolmogorov-Arnold Network-based method for structured mesh generation

引用

PHYSICS OF FLUIDS 2024年第11期36卷

作者： Peng, Jiaming Chen, Xinhai Zhang, Qingyang Deng, Liang Shen, Liming Liu, Jie Natl Univ Def Technol Natl Key Lab Parallel & Distributed Comp Changsha Peoples R China Natl Univ Def Technol Lab Digitizing Software Frontier Equipment Changsha Peoples R China China Aerodynam Res & Dev Ctr Mianyang Peoples R China

Mesh generation is a critical but time-consuming process for stable and accurate numerical simulations. Although multi-layer perceptron-based meshing methods can be effective, they suffer from slow training convergence and heavy reliance on prior datasets. To overcome these problems, we propose the Kolmogorov-Arnold Network-based meshing network, an efficient data-free method for structured mesh generation. The proposed method takes the meshing task as an optimization problem and embeds meshing-related differential equations into the loss function of Kolmogorov-Arnold Networks. It employs two parts to generate meshes efficiently. The Kolmogorov-Arnold Network part introduces learnable activation functions on the edges of the network, which enables the network to learn meshing rules between parametric and computational domains. The physics-informed learning part provides meshing-related information to guide the network training. Finally, the proposed method can produce high-quality structured meshes with a user-defined number of quadrilateral or hexahedral cells through feed-forward prediction. Experiments on different geometries show that the proposed method achieves up to three orders of magnitude improvement in meshing efficiency compared to traditional methods. It also outperforms state-of-the-art multi-layer perceptron-based methods, yielding high-quality meshes in both two-dimensional and three-dimensional cases without prepared data.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

A novel neural network approach for airfoil mesh quality evaluation

引用

JOURNAL OF parallel AND distributed COMPUTING 2022年第0期164卷 123-132页

作者： Chen, Xinhai Gong, Chunye Liu, Jie Pang, Yufei Deng, Liang Chi, Lihua Li, Kenli Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Changsha 410073 Peoples R China Natl Univ Def Technol Lab Software Engn Complex Syst Changsha 410073 Peoples R China China Aerodynam Res & Dev Ctr Mianyang 621000 Sichuan Peoples R China Hunan Univ Coll Comp Sci & Elect Engn Changsha 410073 Peoples R China

Evaluating mesh quality before solving is crucially important for error control in the numerical simulation of airfoils. Traditional mesh quality metrics are used to identify distorted mesh elements by analyzing their geometric shape information like angles and edges. However, these metrics fail to recognize numerical errors stemming from quality attributes such as improper mesh density or distribution. This deficiency has imposed a burden on intensive manual re-evaluation, which heavily increases the meshing cost. In this paper, we introduce deep neural networks to airfoil mesh quality evaluation to improve its automation and efficiency. Specifically, we propose a neural network-based evaluation model, MQNet, accompanied by the first large-scale mesh benchmark dataset, AirfoilSet. MQNet is trained on the dataset to learn the quality-related attributes including mesh orthogonality, smoothness, and density. Thereafter, the trained network can be used as a black box to automatically evaluate and output the overall quality of the airfoil mesh. To demonstrate the effectiveness and generalization behaviors of the proposed network, we establish an MQNet-based mesh generation workflow. Experimental results show that MQNet is small and accurate. It outperforms widely-used neural networks and can be a useful tool to guide the high quality mesh generation process with minimal user intervention. (C) 2022 Elsevier Inc. All rights reserved.

关键词： Numerical simulation Mesh quality Deep neural network Benchmark dataset

来源：评论

学校读者我要写书评

暂无评论

Webformer: Pre-training with Web Pages for Information Retrieval 22

Webformer: Pre-training with Web Pages for Information Retri...

引用

45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)

作者： Guo, Yu Ma, Zhengyi Mao, Jiaxin Qian, Hongjin Zhang, Xinyu Jiang, Hao Cao, Zhao Dou, Zhicheng Renmin Univ China Gaoling Sch Artificial Intelligence Beijing Peoples R China Huawei Distributed & Parallel Software Lab Beijing Peoples R China Beijing Key Lab Big Data Management & Anal Method Beijing Peoples R China Huawei Beijing Peoples R China

ISBN: (纸本)9781450387323

Pre-trained language models (PLMs) have achieved great success in the area of Information Retrieval. Studies show that applying these models to ad-hoc document ranking can achieve better retrieval effectiveness. However, on the Web, most information is organized in the form of HTML web pages. In addition to the pure text content, the structure of the content organized by HTML tags is also an important part of the information delivered on a web page. Currently, such structured information is totally ignored by pre-trained models which are trained solely based on text content. In this paper, we propose to leverage large-scale web pages and their DOM (Document Object Model) tree structures to pre-train models for information retrieval. We argue that using the hierarchical structure contained in web pages, we can get richer contextual information for training better language models. To exploit this kind of information, we devise four pre-training objectives based on the structure of web pages, then pre-train a Transformer model towards these tasks jointly with traditional masked language model objective. Experimental results on two authoritative ad-hoc retrieval datasets prove that our model can significantly improve ranking performance compared to existing pre-trained models.

关键词： Ad-hoc Retrieval Pre-training Web Page DOM Tree

来源：评论

学校读者我要写书评

暂无评论

BGAE: Auto-Encoding Multi-View Bipartite Graph Clustering

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2024年第8期36卷 3682-3696页

作者： Li, Liang Pan, Yuangang Liu, Jie Liu, Yue Liu, Xinwang Li, Kenli Tsang, Ivor W. Li, Keqin Natl Univ Def Technol Sch Comp Changsha 410073 Peoples R China ASTAR Ctr Frontier AI Res Singapore 138632 Singapore Natl Univ Def Technol Sci & Technol & Parallel & Distributed Proc Lab Changsha 410073 Peoples R China Natl Univ Def Technol Lab Software Engn Complex Syst Changsha 410073 Peoples R China Hunan Univ Coll Comp Sci & Elect Engn Changsha 410073 Peoples R China Hunan Univ Supercomp & Cloud Comp Inst Changsha 410073 Peoples R China SUNY Coll New Paltz Dept Comp Sci New Paltz NY 12561 USA

Unsupervised multi-view bipartite graph clustering (MVBGC) is a fast-growing research, due to promising scalability in large-scale tasks. Although many variants are proposed by various strategies, a common design is to construct the bipartite graph directly from the input data, i.e., only consider the unidirectional "encoding" process. However, "encoding-decoding" mechanism is a popular design for deep learning, the most representative one is auto-encoder (AE). Enlightened by this, this paper rethinks existing MVBGC paradigms and transfers the "encoding-decoding" design into graph machine learning, and proposes a novel framework termed auto-encoding multi-view bipartite graph clustering (BGAE), which integrates encoding, bipartite graph construction, and decoding modules in a self-supervised learning manner. The encoding module extracts a latent joint representation from the input data, the bipartite graph construction module learns a bipartite graph with connectivity constraint in latent semantic space, and the decoding module recreates the input data via the bipartite graph. Therefore, our novel BGAE combines representation learning, bipartite graph learning, reconstruction learning, and label inference into a unified framework. All the modules are seamlessly integrated and mutually reinforcing for clustering-friendly purposes. Extensive experiments verify the superiority of our novel design and the significance of "decoding" process. To the best of our knowledge, this is the first attempt to explore "encoding-decoding" design in traditional MVBGC.

关键词： Bipartite graph Decoding Machine learning Encoding Synthetic data Matrix decomposition Image reconstruction Bipartite graph learning encoding-decoding graph machine learning multi-view clustering

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：