检索结果-内蒙古大学图书馆

14th International Conference on Knowledge Science, Engineering, and Management (KSEM)

作者： Sun, Ding Huang, Zhen Li, Dongsheng Ye, Xiangyu Wang, Yilin Natl Univ Def Technol Changsha 410073 Hunan Peoples R China Natl Key Lab Parallel & Distributed Proc Changsha Peoples R China

ISBN: (纸本)9783030821364;9783030821357

Graph embedding is a crucial method to produce node features that can be used for various machine learning tasks. Because of the large number of embedded parameters in large graphs, a single machine cannot load the entire graph into GPUs at once, so a partitioning strategy is required. However, there are some problems with partitioning strategies. Firstly, partitioning introduces data I/O and processing overhead, which increases training time, especially on the cluster with a small number of sites. Secondly, partitioning can affect the performance of the model. For multi-relation graphs, this effect is often negative. To address these problems, we propose the training pipeline and random partitions recombination methods. The training pipeline can reduce the time overhead by masking data loading time to GPU computation, and partitions recombination can effectively improve multi-relation model performance. We conducted experiments on multi-relation graphs and social networks, and the results show that both methods are effective.

关键词： Graph embedding Knowledge graphs Partitioning graph framework GPU distributed graph algorithms

来源：评论

学校读者我要写书评

暂无评论

FedHybrid: Hierarchical Hybrid Training for High-Performance Federated Learning 20

FedHybrid: Hierarchical Hybrid Training for High-Performance...

引用

20th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON)

作者： Chang, Tao Li, Li Wu, Meihan Yu, Wei Wang, Xiaodong Natl Univ Def Technol Natl Key Lab Parallel & Distributed Comp Changsha Hunan Peoples R China Univ Macau State Key Lab Internet Things Smart City Zhuhai Peoples R China China Elect Technol Grp Corp Res Inst 30 Beijing Peoples R China

ISBN: (纸本)9798350300529

Federated Learning coordinates multiple devices to train a shared model while preserving data privacy. Despite its potential benefit, the increasing number of participating devices poses new challenges to the deployment in real-world cases. The highly limited amount of data located on each device coupled with significantly unbalanced data across different devices severely impede the performance of the shared model and the overall training progress at the same time. In this paper, we propose FedHybrid, a hierarchical hybrid training framework for high-performance Federated Learning on a wide scale. Unlike the existing work that mainly focuses on the statistical challenge, FedHybrid establishes a hierarchical hybrid training framework that effectively utilizes the fragmented and unbalanced data located on the participating devices on a wide scale. Specifically, FedHybrid consists of the following two core components, a global coordinator deployed on the central server and a local coordinator deployed on each participating device. The global coordinator organizes the participating devices into different groups through jointly considering the system heterogeneity and unbalanced training data in order to accelerate the overall training progress while guaranteeing the model performance. Within each group, a novel device-to-device (D2D) sequential training procedure is coordinated by the local coordinator to effectively utilize the fragmented and unbalanced training data in order to intelligently update the local models. At the same time, we provide the theoretical analysis of FedHybrid and conduct extensive experiments to evaluate its effectiveness. The results show that FedHybrid effectively improves model accuracy up to 27% and accelerates the whole training process by 20% on average.

关键词： Privacy-preserving techniques

来源：评论

学校读者我要写书评

暂无评论

Calibrated One-Class Classification for Unsupervised Time Series Anomaly Detection

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2024年第11期36卷 5723-5736页

作者： Xu, Hongzuo Wang, Yijie Jian, Songlei Liao, Qing Wang, Yongjun Pang, Guansong Intelligent Game & Decis Lab IGDL Beijing 100091 Peoples R China Natl Univ Def Technol Coll Comp Natl Key Lab Parallel & Distributed Comp Changsha 410073 Hunan Peoples R China Natl Univ Def Technol Coll Comp Changsha 410073 Hunan Peoples R China Harbin Inst Technol Shenzhen Sch Comp Sci & Technol Shenzhen 518055 Guangdong Peoples R China Singapore Management Univ Sch Comp & Informat Syst Singapore 178902 Singapore

Time series anomaly detection is instrumental in maintaining system availability in various domains. Current work in this research line mainly focuses on learning data normality deeply and comprehensively by devising advanced neural network structures and new reconstruction/prediction learning objectives. However, their one-class learning process can be misled by latent anomalies in training data (i.e., anomaly contamination) under the unsupervised paradigm. Their learning process also lacks knowledge about the anomalies. Consequently, they often learn a biased, inaccurate normality boundary. To tackle these problems, this paper proposes calibrated one-class classification for anomaly detection, realizing contamination-tolerant, anomaly-informed learning of data normality via uncertainty modeling-based calibration and native anomaly-based calibration. Specifically, our approach adaptively penalizes uncertain predictions to restrain irregular samples in anomaly contamination during optimization, while simultaneously encouraging confident predictions on regular samples to ensure effective normality learning. This largely alleviates the negative impact of anomaly contamination. Our approach also creates native anomaly examples via perturbation to simulate time series abnormal behaviors. Through discriminating these dummy anomalies, our one-class learning is further calibrated to form a more precise normality boundary. Extensive experiments on ten real-world datasets show that our model achieves substantial improvement over sixteen state-of-the-art contenders.

关键词： Time series analysis Data models Contamination Training Calibration Anomaly detection Uncertainty one-class classification time series anomaly contamination native anomalies

来源：评论

学校读者我要写书评

暂无评论

Cross Modality Knowledge Distillation for Multi-modal Aerial View Object Classification

Cross Modality Knowledge Distillation for Multi-modal Aerial...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yang, Lehan Xu, Kele Univ Sydney Camperdown NSW Australia Key Lab Parallel & Distributed Proc Changsha Peoples R China

ISBN: (纸本)9781665448994

In the case of bad weather or low lighting conditions, a single sensor may not be able to capture enough information for object identification. Compared with the traditional optical image, synthetic aperture radar (SAR) imaging has greater advantages, such as the ability to penetrate through fog and smoke. However, SAR images are of low resolution and contaminated by high-level speckle noise. As a result, it is of great difficulty to extract powerful and robust features from the SAR images. In this paper, we explored whether multiple imaging modalities can improve the object detection performance. Here, we propose a Cross Modality Knowledge Distillation (CMKD) paradigm, and explore two different network structures named CMKD-s and CMKD-m for the object classification task. Specifically, CMKD-s transfers the information captured by the two sensors using the online knowledge distillation, which can achieve cross-modal knowledge sharing and enhance the robustness of the aerial view object classification model. Moreover, leveraging the semi-supervised enhanced training, we proposed a novel method named CMKD-m, which strengthens the model for mutual knowledge transfer. Through quantitative comparison, we found that CMKD-s and CMKD-m outperform the method without knowledge transfer, on the NTIRE2021 SAR-EO challenge dataset.

关键词： Training Speckle Feature extraction Radar polarimetry Data models Robustness Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

An adaptive gradient correction method based on mesh skewness for finite volume fluid dynamics simulations

引用

PHYSICS OF FLUIDS 2025年第1期37卷

作者： Song, Min Li, Chao Guo, Xiaowei 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 410073 Hunan Peoples R China

In unstructured mesh solvers based on the finite volume method, accurate gradient calculation is crucial for determining the accuracy of equations. However, most mainstream computational fluid dynamics (CFD) software offer only uncorrected or globally corrected gradient options, which do not take into account local geometric characteristics. This limitation hampers computational efficiency and accuracy, especially in complex geometries, leading to poor convergence or even divergence, thus constraining its practical application in real-world engineering problems. To address these issues, this paper presents an adaptive gradient correction algorithm based on mesh skewness. By analyzing the geometric characteristics of mesh cells and dynamically applying a correction value, the algorithm modifies the gradient calculation formula adaptively to reduce numerical errors and improve accuracy, while ensuring stability. The algorithm has been successfully implemented in a general-purpose CFD software and validated through complex engineering cases such as sub-channel analysis, demonstrating its practical engineering value. Results indicate that for turbulent flow through a pipe, the proposed adaptive correction algorithm achieves an improved accuracy, demonstrating high precision and superiority in capturing intricate details of turbulence. In more complex scenarios like sub-channel analysis, the adaptive correction algorithm yields an error of 2.54% compared to 4.03% for the uncorrected approach. Unlike global correction methods that may lead to computational divergence within a few iterations, the adaptive correction method consistently maintains stability, accelerates convergence, and improves accuracy, offering significant theoretical and practical value.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

A unified deep framework for peptide-major histocompatibility complex-T cell receptor binding prediction

引用

NATURE MACHINE INTELLIGENCE 2025年第4期7卷 1-11页

作者： Zhao, Yunxiang Yu, Jijun Su, Yixin Shu, You Ma, Enhao Wang, Jing Jiang, Shuyang Wei, Congwen Li, Dongsheng Huang, Zhen Cheng, Gong Ren, Hongguang Feng, Jiannan Beijing Inst Biotechnol Lab Adv Biotechnol Beijing Peoples R China Beijing Inst Pharmacol & Toxicol Beijing Key Lab Therapeut Gene Engn Antibody Beijing Peoples R China Huazhong Univ Sci & Technol Sch Comp Sci & Technol Wuhan Peoples R China Natl Univ Def Technol Coll Comp Sci & Technol Natl Key Lab Parallel & Distributed Comp Changsha Peoples R China Tsinghua Univ Sch Basic Med Sci Beijing Peoples R China Jilin Univ Coll Math Changchun Peoples R China Shenzhen Bay Lab Inst Infect Dis Shenzhen Peoples R China

Antigen peptides that are presented by a major histocompatibility complex (MHC) and recognized by a T cell receptor (TCR) have an essential role in immunotherapy. Although substantial progress has been made in predicting MHC presentation, accurately predicting the binding interactions between antigen peptides, MHCs and TCRs remains a major computational challenge. In this paper, we propose a unified deep framework (called UniPMT) for peptide, MHC and TCR binding prediction to predict the binding between the peptide and the CDR3 of TCR beta in general, presented by class I MHCs. UniPMT is comprehensively validated by a series of experiments and achieved state-of-the-art performance in the peptide-MHC-TCR, peptide-MHC and peptide-TCR binding prediction tasks with up to 15% improvements in area under the precision-recall curve taking the peptide-MHC-TCR binding prediction task as an example. In practical applications, UniPMT shows strong predictive power, correlates well with T cell clonal expansion and outperforms existing methods in neoantigen-specific binding prediction with up to 17.62% improvements in area under the precision-recall curve on experimentally validated datasets. Moreover, UniPMT provides interpretable insights into the identification of key binding sites and the quantification of peptide-MHC-TCR binding probabilities. In summary, UniPMT shows great potential to serve as a useful tool for antigen peptide discovery, disease immunotherapy and neoantigen vaccine design.

关键词： Peptides

来源：评论

学校读者我要写书评

暂无评论

QSIM: A novel approach to node proximity estimation based on Discrete-time quantum walk

引用

APPLIED INTELLIGENCE 2021年第4期51卷 2574-2588页

作者： Wang, Xin Lu, Kai Zhang, Yi Liu, Kai Natl Univ Def Technol Coll Comp Sci Changsha Peoples R China Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Changsha Peoples R China

Node proximity estimation studies structural similarity between nodes and is the key issue of network analysis. It can exist as the node recommendation task and is a fundamental basis of other graph mining techniques. Although Discrete-time quantum walk (DTQW), a promising new technique with distinctive characters, is widely used in many graph mining problems such as graph isomorphism and graph kernel, there are only a few works estimating proximity via DTQW, limiting the further application of DTQW in graph mining. In this paper, we study the capability of DTQW for proximity estimation and propose QSIM to estimate node proximity by DTQW. By analyzing the diffusion process of biased walks, we discover two influential effects that are beneficial to proximity estimation. The Diminishing Effect shows that a node close to the starting node can generally have a high average probability during the diffusion process, which serves as the basis of QSIM. The Returning Effect shows the probability has a tendency to stay around the starting node during the diffusion, which enhances the capability for mining local information especially in densely-connected structures. Benefited from the two effects, QSIM faithfully reveals node proximity and comprehensively unifies different kinds of node proximity. QSIM is the first mature quantum-walk-based method for proximity estimation. Extensive experiments validate the effectiveness of QSIM and show that QSIM outperforms state-of-the-art methods in the node recommendation task, significantly surpassing Refex, Node2vec, and Role2vec, by up to 1094.2% in the first-order node proximity and 18.8% in the second-order node proximity.

关键词： Quantum walk Discrete-time quantum walk Node proximity estimation Network analysis

来源：评论

学校读者我要写书评

暂无评论

SIFTER: A Framework for Robust Rumor Detection

引用

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE procESSING 2022年 30卷 429-442页

作者： Lu, Menglong Huang, Zhen Li, Binyang Zhao, Yunxiang Qin, Zheng Li, DongSheng Natl Univ Def Technol Sci & Technol Parallel & Distributed Lab Changsha 410073 Peoples R China Univ Int Relat Beijing 100091 Peoples R China Beijing Inst Biotechnol State Key Lab Pathogen & Biosecur Beijing 100071 Peoples R China

With the development of online social media, the fabrication and dissemination of rumors are much easier than before. As a result, automatic rumor detection becomes more urgent for internet governors, and has received great interest from the AI community. Even though many initial successes have been achieved in terms of detection accuracy and timeliness, existing rumor detection methods are still not robust due to the frequent domain shift problem and the inconsistent propagation problem. Frequent domain shift refers that rumors' topic changes frequently on online social media, so the trained model may expire quickly in real applications. Inconsistent propagation is another practical challenge, referring to the fact that the spread of rumors is often accompanied by misleading comments. Therefore, a vulnerable model may output inconsistent predictions for the same instance. In this paper, we propose a new framework to improve the robustness of existing rumor detection methods, named SIFTER (Subjective InFormaTion Enhanced Reinforcement learning). To address the frequent domain shift, SIFTER employs multi-task learning to introduce external knowledge that can explicitly describe rumors, and thus makes models more adaptive across domains. In particular, SIFTER involves a multi-task learning module to capture subjective information, which is found to be discriminative in rumors' propagations. To address the inconsistent propagation, SIFTER employs reinforcement learning to realize a new training schema tailed for rumor detection, namely sequential training, which can reduce the attendance of noisy comments in the feature extraction process. Experimental results on two benchmark datasets, Twitter and Weibo, validate the effectiveness of SIFTER. After migrating existing methods to SIFTER, their accuracy score is improved up to 9.4% in cross-domain inference, and their reverse ratio decreases by nearly 4% in continuous prediction.

关键词： Training Feature extraction Social networking (online) Predictive models Noise measurement Task analysis Multitasking Rumor subjectivity rumor detection reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

2PGraph: Accelerating GNN Training over Large Graphs on GPU Clusters

2PGraph: Accelerating GNN Training over Large Graphs on GPU ...

引用

IEEE International Conference on Cluster Computing (Cluster)

作者： Zhang, Lizhi Lai, Zhiquan Li, Shengwei Tang, Yu Liu, Feng Li, Dongsheng Natl Univ Def Technol Natl Lab Parallel & Distributed Proc PDL Comp Coll Changsha Peoples R China

ISBN: (纸本)9781728196664

Graph neural networks (GNNs) have been emerging as powerful learning tools for unstructured data and successfully applied to many graph-based application domains. Sampling-based graph training is commonly used in existing GNN training frameworks to handle large-scale graphs. However, this type of approach is restricted by the problems of long memory accessing latency, neighborhood explosion during mini-batch sampling, and inefficient loading of vertex features from CPU to GPU. In this paper, we propose 2PGraph, a system that supports high-speed locality-aware mini-batch sampling and GNN layer-aware feature caching. 2PGraph significantly reduces sampling time by vertex-cluster sampling, which improves the locality of vertex access and limits the range of neighborhood expansion. To further reduce the sampling time in a distributed environment, we renumber the vertex numbers in subgraphs after graph partition, which improves the data locality of each partition. 2PGraph also avoids abundant data transfer between CPU and GPU through the feature data caching on available GPU resources with a hit rate of 100 %. Furthermore, 2PGraph develops a GNN layer-aware feature caching policy during data parallel training and achieves better cache efficiency and memory utilization. We evaluate 2PGraph against two state-of-the-art industrial GNN frameworks, i.e., PyG and DGL, on a diverse array of benchmarks. Experimental results show that 2PGraph reduces up to 90 % mini-batch sampling and 99 % data loading time, and achieves up to 8.7 x performance speedup over the state-of-the-art baselines on an 8-GPU cluster.

关键词： graph neural networks pipeline parallel data parallel sampling data caching

来源：评论

学校读者我要写书评

暂无评论

CSR&RV: An Efficient Value Compression Format for Sparse Matrix-Vector Multiplication 19th

CSR&RV: An Efficient Value Compression Format for Sparse Mat...

引用

19th International Conference on Network and parallel Computing (NPC)

作者： Yan, Junjun Chen, Xinhai Liu, Jie 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

ISBN: (纸本)9783031213946;9783031213953

Sparse Matrix-Vector Multiplication (SpMV) plays a critical role in many areas of science and engineering applications. The storage space of value array in general real sparse matrices accounts for costly. However, the existing compressed formats cannot balance the compressed rate and computational speed. To address this issue, we propose an efficient value compression format implemented by AVX512 instructions called Compressed Sparse Row and Repetition Value (CSR&RV). This format stores each different value once and uses the indexes array to store the position of values, which reduces the storage space by compressing the value array. We conduct a series of experiments on an Intel Xeon processor and compare it with five other formats in 30 real-world matrices. Experimental results show that CSR&RV can achieve a speedup up to 3.86x (1.66x on average) and a speedup up to 12.42x (3.12x on average) for single-core and multi-core throughput, respectively. Meanwhile, our format can reduce the memory space by 48.57% on average.

关键词： Sparse matrix-vector multiplication Value compression Storage format AVX512

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：