检索结果-内蒙古大学图书馆

Balancing communication overhead and accuracy in compression integration: a survey

Journal of Supercomputing 2025年第8期81卷 1-63页

作者： Yang, Aiqiang Liu, Jie Yang, Bo Mo, Zeyao Li, Keqin College of Computer Science and Technology National University of Defense Technology Changsha410000 China Laboratory of Digitizing Software for Frontier Equipment National University of Defense Technology Changsha410073 China National Key Laboratory of Parallel and Distributed Computing National University of Defense Technology Changsha410073 China China Academy of Engineering Physics Beijing China Department of Computer Science State University of New York New PaltzNY12561 United States

In large-scale distributed training, communication compression techniques are widely used to reduce the significant communication overhead caused by the frequent exchange of model parameters or gradients between training nodes. However, these techniques often introduce additional computational complexity and may lead to data loss, thereby affecting model convergence and performance. This review examines key optimization methods in communication compression, including pruning techniques that remove irrelevant weights, quantization techniques that convert floating-point parameters to low-precision representations, and sparsification techniques that transmit only critical gradients. Low-rank approximation techniques, which compress parameters through matrix factorization, are particularly useful for large-scale models. These techniques have also been widely applied in various application scenarios, demonstrating their effectiveness in different environments. Application scenarios include distributed training, federated learning, and edge computing, where bottlenecks are carefully identified and evaluated in common scenarios, providing a basis for further optimization. Future development directions emphasize co-design of hardware and algorithms, dynamic strategies, and cross-layer optimization. This study provides valuable comparisons of key methods and theoretical analysis for efficient communication compression in distributed systems. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

A prompt-based approach to adversarial example generation and robustness enhancement

引用

Frontiers of Computer science 2024年第4期18卷 85-96页

作者： Yuting YANG Pei HUANG Juan CAO Jintao LI Yun LIN Feifei MA Key Lab of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing 100190China School of Computer Science and Technology University of Chinese Academy of SciencesBeijing 100049China Department of Computer Science Stanford UniversityCA 94305USA School of Computing National University of SingaporeSingapore 119077Singapore Laboratory of Parallel Software and Computational Science Institute of SoftwareChinese Academy of SciencesBeijing 100190China

Recent years have seen the wide application of natural language processing(NLP)models in crucial areas such as finance,medical treatment,and news media,raising concerns about the model robustness and *** find that prompt paradigm can probe special robust defects of pre-trained language *** prompt texts are first constructed for inputs and a pre-trained language model can generate adversarial examples for victim models via *** results show that prompt paradigm can efficiently generate more diverse adversarial examples besides synonym ***,we propose a novel robust training approach based on prompt paradigm which incorporates prompt texts as the alternatives to adversarial examples and enhances robustness under a lightweight minimax-style optimization *** on three real-world tasks and two deep neural models show that our approach can significantly improve the robustness of models to resist adversarial attacks.

关键词： robustness adversarial example prompt learning pre-trained language model

来源：评论

学校读者我要写书评

暂无评论

MeshONet: A Generalizable and Efficient Operator Learning Method for Structured Mesh Generation

arXiv

引用

arXiv 2025年

作者： Xiao, Jing Chen, Xinhai Peng, Jiaming Wang, Qingling Liu, Jie Laboratory of Digitizing Software for Frontier Equipment Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha410073 China

Mesh generation plays a crucial role in scientific computing. Traditional mesh generation methods, such as TFI and PDE-based methods, often struggle to achieve a balance between efficiency and mesh quality. To address this challenge, physics-informed intelligent learning methods have recently emerged, significantly improving generation efficiency while maintaining high mesh quality. However, physics-informed methods fail to generalize when applied to previously unseen geometries, as even small changes in the boundary shape necessitate burdensome retraining to adapt to new geometric variations. In this paper, we introduce MeshONet, the first generalizable intelligent learning method for structured mesh generation. The method transforms the mesh generation task into an operator learning problem with multiple input and solution functions. To effectively overcome the multivariable mapping restriction of operator learning methods, we propose a dual-branch, shared-trunk architecture to approximate the mapping between function spaces based on input-output pairs. Experimental results show that MeshONet achieves a speedup of up to four orders of magnitude in generation efficiency over traditional methods. It also enables generalization to different geometries without retraining, greatly enhancing the practicality of intelligent methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

parallelization of Fast Monte Carlo Dose Calculation for Radiotherapy Treatment Planning on the ARMv8 Architecture 11

Parallelization of Fast Monte Carlo Dose Calculation for Rad...

引用

11th International Conference on Information science and technology, ICIST 2021

作者： Jin, Chi Wang, Qinglin Zhao, Yang Dou, Yong National University of Defense Technology Science and Technology on Parallel and Distributed Processing Laboratory Changsha China

ISBN: (纸本)9781665412667

Monte Carlo (MC) simulation plays a key role in radiotherapy. Since the simulation time of the MC program cannot fully meet the clinical requirements, we use the ARM-based FT-2000+ multi-core processor for parallelization, which provides an effective solution for accelerating MC dose calculation. In this paper, we implement and verify FT-DPM, which is an OpenMP-based MC Dose Planning Method on FT-2000+. FT-DPM utilizes the parallelism of MC simulation and the advantage of ARM architecture to achieve the parallelization on ARM architecture. Meanwhile, we optimize the original DPM program in terms of memory allocation, data structure and data type. The experiments show that, compared with the original DPM code, FT-DPM obtains very accurate results and reaches the maximum speedups of 155.94 times for the electron case. The parallel program based on FT-2000+ only takes 44.1 seconds to simulate the particle transport of 100 million times, showing good clinical application potential. In addition, the speedup and efficiency of FT-DPM running on different core counts are also discussed. © 2021 IEEE.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Transfer learning for deep neural network-based partial differential equations solving

引用

Advances in Aerodynamics 2021年第1期3卷 635-648页

作者： Xinhai Chen Chunye Gong Qian Wan Liang Deng Yunbo Wan Yang Liu Bo Chen Jie Liu Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense TechnologyChangshaChina China Aerodynamics Research and Development Center MianyangChina.

Deep neural networks(DNNs)have recently shown great potential in solving partial differential equations(PDEs).The success of neural network-based surrogate models is attributed to their ability to learn a rich set of solution-related ***,learning DNNs usually involves tedious training iterations to converge and requires a very large number of training data,which hinders the application of these models to complex physical *** address this problem,we propose to apply the transfer learning approach to DNN-based PDE solving *** our work,we create pairs of transfer experiments on Helmholtz and Navier-Stokes equations by constructing subtasks with different source terms and Reynolds *** also conduct a series of experiments to investigate the degree of generality of the features between different *** results demonstrate that despite differences in underlying PDE systems,the transfer methodology can lead to a significant improvement in the accuracy of the predicted solutions and achieve a maximum performance boost of 97.3%on widely used surrogate models.

关键词： Deep neural network Partial differential equation Surrogate model Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Large-scale graph processing systems: a survey

引用

信息与电子工程前沿（英文版） 2020年第3期21卷 384-404页

作者： Ning LIU Dong-sheng LI Yi-ming ZHANG Xiong-lve LI Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense TechnologyChangsha 410000China

Graph is a significant data structure that describes the relationship between entries. Many application domains in the real world are heavily dependent on graph data. However, graph applications are vastly different from traditional applications. It is inefficient to use general-purpose platforms for graph applications, thus contributing to the research of specific graph processing platforms. In this survey, we systematically categorize the graph workloads and applications, and provide a detailed review of existing graph processing platforms by dividing them into general-purpose and specialized systems. We thoroughly analyze the implementation technologies including programming models, partitioning strategies, communication models, execution models, and fault tolerance strategies. Finally, we analyze recent advances and present four open problems for future research.

关键词： Graph workloads Graph applications Graph processing systems

来源：评论

学校读者我要写书评

暂无评论

Jammer Localization for Wireless Sensor Networks

引用

Chinese Journal of Electronics 2023年第4期20卷 735-738页

作者： SUN Yanqiang WANG Xiaodong ZHOU Xingming National Key Laboratory for Parallel and Distributed Processing College of Computer Science National University of Defense Technology Changsha China

Jamming attack can severely affect the performance of Wireless sensor networks (WSNs) due to the broadcast nature of wireless medium. In order to localize the source of the attacker, we in this paper propose a jammer localization algorithm named as Minimum-circle-covering based localization (MCCL). Comparing with the existing solutions that rely on the wireless propagation parameters, MCCL only depends on the location information of sensor nodes at the border of the jammed region. MCCL uses the plane geometry knowledge, especially the minimum circle covering technique, to form an approximate jammed region, and hence the center of the jammed region is treated as the estimated position of the jammer. Simulation results showed that MCCL is able to achieve higher accuracy than other existing solutions in terms of jammer's transmission range and sensitivity to nodes' density.

关键词： Location awareness Wireless communication Geometry Wireless sensor networks Sensitivity Simulation Jamming

来源：评论

学校读者我要写书评

暂无评论

3DMeshNet: A Three-Dimensional Differential Neural Network for Structured Mesh Generation

arXiv

引用

arXiv 2024年

作者： Peng, Jiaming Chen, Xinhai Liu, Jie Laboratory of Digitizing Software for Frontier Equipment Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha410073 China

Mesh generation is a crucial step in numerical simulations, significantly impacting simulation accuracy and efficiency. However, generating meshes remains time-consuming and requires expensive computational resources. In this paper, we propose a novel method, 3DMeshNet, for three-dimensional structured mesh generation. The method embeds the meshing-related differential equations into the loss function of neural networks, formulating the meshing task as an unsupervised optimization problem. It takes geometric points as input to learn the potential mapping between parametric and computational domains. After suitable offline training, 3DMeshNet can efficiently output a three-dimensional structured mesh with a user-defined number of quadrilateral/hexahedral cells through the feed-forward neural prediction. To enhance training stability and accelerate convergence, we integrate loss function reweighting through weight adjustments and gradient projection alongside applying finite difference methods to streamline derivative computations in the loss. Experiments on different cases show that 3DMeshNet is robust and fast. It outperforms neural network-based methods and yields superior meshes compared to traditional mesh partitioning methods. 3DMeshNet significantly reduces training times by up to 85% compared to other neural network-based approaches and lowers meshing overhead by 4 to 8 times relative to traditional meshing methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Smoothing Point Adjustment-Based Evaluation of Time Series Anomaly Detection

Smoothing Point Adjustment-Based Evaluation of Time Series A...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Mingyu Liu Yijie Wang Hongzuo Xu Xiaohui Zhou Bin Li Yongjun Wang Science and Technology on Parallel and Distributed Processing Laboratory College of Computer National University of Defense Technology Changsha China

Anomalies in time series appear consecutively, forming anomaly segments. Applying the classical point-based evaluation metrics to evaluate the detection performance of segments leads to considerable underestimation, so most related studies resort to point adjustment. This operation treats all points as true positives within a segment equally when only one individual point alarms, resulting in significant overestimation and creating an illusion of superior performance. This paper proposes smoothing point adjustment, a novel range-based evaluation protocol for time series anomaly detection. Our protocol reflects detection performance impartially by carefully considering the specific location and frequency of alarms in the raw results. It is achieved by smoothly determining the adjustment range and rewarding early detection via a ranging function and a rewarding function. Compared with other evaluation metrics, experiments on different datasets show that our protocol can yield a performance ranking of various methods more consistent with the desired situation.

关键词： Protocols Smoothing methods Time series analysis Detectors Signal processing Distance measurement Acoustics

来源：评论

学校读者我要写书评

暂无评论

Implicit Neural Alignment Network for Arbitrary-scale Space-Time Video Super-Resolution

Implicit Neural Alignment Network for Arbitrary-scale Space-...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Qin Jiang Qinglin Wang Lihua Chi Jie Liu Science and Technology on Parallel and Distributed Processing Laboratory Laboratory of Digitizing Software for Frontier Equipment Hunan GuoKe Computility Technology Co. Ltd

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Space-time video super-resolution (STVSR) is a comprehensive task comprising two subtasks: video super resolution in space dimension and video frame interpolation in time dimension. Conventional decoupled two-stage approaches tend to overlook the intrinsic correlation between the two tasks. Overcoming this challenge requires the development of a unified model capable of simultaneously implementing space-time super-resolution across arbitrary scales. Most existing models are confined to training on fixed space upsampling scales or specific frame-rate videos, resulting in limited generalization capabilities for flexible space-time super-resolution scenarios. In response to this limitation, our approach draws inspiration from continuous implicit neural representation. We propose an enhanced Implicit Neural Alignment Network (INAN) based on the VideoINR framework, encompassing feature refinement, precise motion flow estimation, and multi-scale feature fusion to optimize the final implicit neural decoding. Our extensive experimental evaluations on multiple benchmarks underscore the efficacy of the INAN model, indicate its superior performance compared to prior STVSR methods.

关键词： Training Interpolation Correlation Superresolution Neural networks Estimation Benchmark testing

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：