检索结果-内蒙古大学图书馆

AutoQNN: An End-to-End Framework for Automatically Quantizing Neural Networks

Journal of computer Science & technology 2024年第2期39卷 401-420页

作者：龚成卢冶代素蓉邓倩杜承昆李涛 College of Software Nankai UniversityTianjin 300350China College of Computer Science Nankai UniversityTianjin 300350China State Key Laboratory of Processors Institute of Computing TechnologyChinese Academy of Sciences Beijing 100190China

Exploring the expected quantizing scheme with suitable mixed-precision policy is the key to compress deep neural networks(DNNs)in high efficiency and *** exploration implies heavy workloads for domain experts,and an automatic compression method is ***,the huge search space of the automatic method introduces plenty of computing budgets that make the automatic process challenging to be applied in real *** this paper,we propose an end-to-end framework named AutoQNN,for automatically quantizing different layers utilizing different schemes and bitwidths without any human *** can seek desirable quantizing schemes and mixed-precision policies for mainstream DNN models efficiently by involving three techniques:quantizing scheme search(QSS),quantizing precision learning(QPL),and quantized architecture generation(QAG).QSS introduces five quantizing schemes and defines three new schemes as a candidate set for scheme search,and then uses the Differentiable Neural Architecture Search(DNAS)algorithm to seek the layer-or model-desired scheme from the *** is the first method to learn mixed-precision policies by reparameterizing the bitwidths of quantizing schemes,to the best of our *** optimizes both classification loss and precision loss of DNNs efficiently and obtains the relatively optimal mixed-precision model within limited model size and memory *** is designed to convert arbitrary architectures into corresponding quantized ones without manual intervention,to facilitate end-to-end neural network *** have implemented AutoQNN and integrated it into *** experiments demonstrate that AutoQNN can consistently outperform state-of-the-art *** 2-bit weight and activation of AlexNet and ResNet18,AutoQNN can achieve the accuracy results of 59.75%and 68.86%,respectively,and obtain accuracy improvements by up to 1.65%and 1.74%,respectively,compared with state-of-the-art ***,c

关键词： automatic quantization mixed precision quantizing scheme search quantizing precision learning quan-tized architecture generation

来源：评论

学校读者我要写书评

暂无评论

BGNN: Behavior-aware graph neural network for heterogeneous session-based recommendation

引用

Frontiers of computer Science 2023年第5期17卷 103-118页

作者： Jinwei LUO Mingkai HE Weike PAN Zhong MING College of Computer Science and Software Engineering Shenzhen UniversityShenzhen 518060China National Engineering Laboratory for Big Data System Computing Technology Shenzhen UniversityShenzhen 518060China

Session-based recommendation(SBR)and multibehavior recommendation(MBR)are both important problems and have attracted the attention of many researchers and *** from SBR that solely uses one single type of behavior sequences and MBR that neglects sequential dynamics,heterogeneous SBR(HSBR)that exploits different types of behavioral information(e.g.,examinations like clicks or browses,purchases,adds-to-carts and adds-to-favorites)in sequences is more consistent with real-world recommendation scenarios,but it is rarely *** efforts towards HSBR focus on distinguishing different types of behaviors or exploiting homogeneous behavior transitions in a sequence with the same type of ***,all the existing solutions for HSBR do not exploit the rich heterogeneous behavior transitions in an explicit way and thus may fail to capture the semantic relations between different types of ***,all the existing solutions for HSBR do not model the rich heterogeneous behavior transitions in the form of graphs and thus may fail to capture the semantic relations between different types of *** limitation hinders the development of HSBR and results in unsatisfactory *** a response,we propose a novel behavior-aware graph neural network(BGNN)for *** BGNN adopts a dual-channel learning strategy for differentiated modeling of two different types of behavior sequences in a ***,our BGNN integrates the information of both homogeneous behavior transitions and heterogeneous behavior transitions in a unified *** then conduct extensive empirical studies on three real-world datasets,and find that our BGNN outperforms the best baseline by 21.87%,18.49%,and 37.16%on average correspondingly.A series of further experiments and visualization studies demonstrate the rationality and effectiveness of our *** exploratory study on extending our BGNN to handle more than two types of behaviors show that our BGNN can e

关键词： session-based recommendation graph neural network heterogeneous behaviors

来源：评论

学校读者我要写书评

暂无评论

YOLO-RLC:An Advanced Target-Detection Algorithm for Surface Defects of Printed Circuit Boards Based on YOLOv5

引用

computers, Materials & Continua 2024年第9期80卷 4973-4995页

作者： Yuanyuan Wang Jialong Huang Md Sharid Kayes Dipu Hu Zhao Shangbing Gao Haiyan Zhang Pinrong Lv School of Computer and Software Engineering Huaiyin Institute of TechnologyHuai’an223003China Huaiyin Institute of Technology Laboratory for Internet of Things and Mobile Internet Technology of Jiangsu ProvinceHuai’an223001China Jiangsu Kesheng Xuanyi Technology Co. Ltd.Huai’an223300China

Printed circuit boards(PCBs)provide stable connections between electronic ***,defective printed circuit boards may cause the entire equipment system to malfunction,resulting in incalculable ***,it is crucial to detect defective printed circuit boards during the generation *** detection methods have low accuracy in detecting subtle defects in complex background *** order to improve the detection accuracy of surface defects on industrial printed circuit boards,this paper proposes a residual large kernel network based on YOLOv5(You Only Look Once version 5)for PCBs surface defect detection,called YOLO-RLC(You Only Look Once-Residual Large Kernel).Build a deep large kernel backbone to expand the effective field of view,capture global informationmore efficiently,and use 1×1 convolutions to balance the depth of the model,improving feature extraction efficiency through reparameterization *** neck network introduces a bidirectional weighted feature fusion network,combined with a brand-new noise filter and feature enhancement extractor,to eliminate noise information generated by information fusion and recalibrate information from different channels to improve the quality of deep *** the aspect ratio of the bounding box to alleviate the issue of specificity *** training and testing on the PCB defect dataset,our method achieved an average accuracy of 97.3%(mAP50)after multiple experiments,which is 4.1%higher than YOLOv5-S,with an average accuracy of 97.6%and an Frames Per Second of *** comparative analysis also proves the superior performance and feasibility of YOLO-RLC in PCB defect detection.

关键词： Deep learning PCB defect detection large kernel noise filtering weighted fusion YOLO

来源：评论

学校读者我要写书评

暂无评论

Analysis and Classification of Fake News Using Sequential Pattern Mining

引用

Big Data Mining and Analytics 2024年第3期7卷 942-963页

作者： M.Zohaib Nawaz M.Saqib Nawaz Philippe Fournier-Viger Yulin He College of Computer Science and Software Engineering Shenzhen UniversityShenzhen 518060 Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ) Shenzhen 518107China Department of Computer Science Faculty of Computing and Information TechnologyUnivesity of SargodhaSargodha 40100Pakistan

Disinformation,often known as fake news,is a major issue that has received a lot of attention *** researchers have proposed effective means of detecting and addressing *** machine and deep learning based methodologies for classification/detection of fake news are content-based,network(propagation)based,or multimodal methods that combine both textual and visual *** introduce here a framework,called FNACSPM,based on sequential pattern mining(SPM),for fake news analysis and *** this framework,six publicly available datasets,containing a diverse range of fake and real news,and their combination,are first transformed into a proper ***,algorithms for SPM are applied to the transformed datasets to extract frequent patterns(and rules)of words,phrases,or linguistic *** obtained patterns capture distinctive characteristics associated with fake or real news content,providing valuable insights into the underlying structures and commonalities of ***,the discovered frequent patterns are used as features for fake news *** framework is evaluated with eight classifiers,and their performance is assessed with various *** experiments were performed and obtained results show that FNACSPM outperformed other state-of-the-art approaches for fake news classification,and that it expedites the classification task with high accuracy.

关键词： disinformation fake news sequential pattern mining(SPM) frequent patterns classification

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Learning with Feature Alignment via Knowledge Distillation 21st

Personalized Federated Learning with Feature Alignment via...

引用

21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024

作者： Qi, Guangfei Qu, Zhihao Lyu, Shen-Huan Jia, Ninghui Ye, Baoliu Key Laboratory of Water Big Data Technology of Ministry of Water Resources College of Computer Science and Software Engineering Hohai University Nanjing China National Key Laboratory for Novel Software Technology Nanjing University Nanjing China

ISBN: (纸本)9789819601189

Personalized Federated Learning (PFL) has gained significant attention for its ability to handle heterogeneous data effectively. Parameter decoupling is a typical approach to PFL. It decouples the model into a feature extractor and a classifier head, where the feature extractor is trained collaboratively to learn a common representation and the classifier head is personalized for local data. Since local training only learns personalized feature information and ignores global information, the generalization ability of the feature extractor is limited. To improve the performance of the local model, a feasible approach is to make the local feature extractor more generalized. However, prior work requires the transmission of additional feature data beyond the transmission of model parameters, which leads to privacy leakage and higher communication overhead. To address these shortcomings, we propose a PFL algorithm with feature alignment via knowledge distillation, named PFAKD. PFAKD enhances the training of local feature extractors by explicitly aligning each sample’s local features with global features, providing more detailed guidance. Meanwhile, it avoids additional communication overhead and the risk of privacy leakage. We conduct extensive experiments in heterogeneous data scenarios. PFAKD outperforms other state-of-the-art methods by up to 4.35% in terms of model accuracy. Our code is available at https://***/fei0829/PFAKD. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A path planning method based on deep reinforcement learning for crowd evacuation

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第6期15卷 2925-2939页

作者： Meng, Xiangdong Liu, Hong Li, Wenhao School of Information Science and Engineering Shandong Normal University Jinan250014 China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan250014 China

Deep reinforcement learning (DRL) is suitable for solving complex path-planning problems due to its excellent ability to make continuous decisions in a complex environment. However, the increase in the population size in the crowd evacuation path-planning problem causes a substantial computational burden for the algorithm, which leads to an unsatisfactory efficiency of the current DRL algorithm. This paper presents a path planning method based on DRL for crowd evacuation to solve the problem. First, we divide crowds into groups based on their relationship and distance from each other and select leaders from them. Next, we expand the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) to propose an Optimized Multi-Agent Deep Deterministic Policy Gradient (OMADDPG) algorithm to obtain the global evacuation path. The OMADDPG algorithm uses the Cross-Entropy Method (CEM) to optimize policy and improve the neural network’s training efficiency by applying the Data Pruning (DP) algorithm. In addition, the social force model is improved, incorporating the relationship between individuals and psychological factors into the model. Finally, this paper combines the improved social force model and the OMADDPG algorithm. The OMADDPG algorithm transmits the path information to the leaders. Pedestrians in the environment are driven by the improved social force model to follow the leaders to complete the evacuation simulation. The method can use a leader to guide pedestrians safely arrive the exit and reduce evacuation time in different environments. The simulation results prove the efficiency of the path planning method. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Towards optimized tensor code generation for deep learning on sunway many-core processor

引用

Frontiers of computer Science 2024年第2期18卷 1-15页

作者： Mingzhen LI Changxi LIU Jianjin LIAO Xuegui ZHENG Hailong YANG Rujun SUN Jun XU Lin GAN Guangwen YANG Zhongzhi LUAN Depei QIAN State Key Laboratory of Software Development Environment Beijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China National University of Singapore Singapore 119077Singapore State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi 214000China Science and Technology on Special System Simulation Laboratory Beijing Simulation Center Beijing 100854China Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China

The flourish of deep learning frameworks and hardware platforms has been demanding an efficient compiler that can shield the diversity in both software and hardware in order to provide application *** the existing deep learning compilers,TVM is well known for its efficiency in code generation and optimization across diverse hardware *** the meanwhile,the Sunway many-core processor renders itself as a competitive candidate for its attractive computational power in both scientific computing and deep learning *** paper combines the trends in these two ***,we propose swTVM that extends the original TVM to support ahead-of-time compilation for architecture requiring cross-compilation such as *** addition,we leverage the architecture features during the compilation such as core group for massive parallelism,DMA for high bandwidth memory transfer and local device memory for data locality,in order to generate efficient codes for deep learning workloads on *** experiment results show that the codes generated by swTVM achieve 1.79x improvement of inference latency on average compared to the state-of-the-art deep learning framework on Sunway,across eight representative *** work is the first attempt from the compiler perspective to bridge the gap of deep learning and Sunway processor particularly with productivity and efficiency in *** believe this work will encourage more people to embrace the power of deep learning and Sunwaymany-coreprocessor.

关键词： sunway processor deep learning compiler code generation performance optimization

来源：评论

学校读者我要写书评

暂无评论

Contextual Structure Knowledge Transfer for Graph Neural Networks 39

Contextual Structure Knowledge Transfer for Graph Neural Net...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Yu, Zhiyuan Li, Wenzhong Yin, Zhangyue Hong, Xiaobin Xiao, Shijian Lu, Sanglu State Key Laboratory for Novel Software Technology Nanjing University China School of Computer Science Fudan University China

ISBN: (纸本)157735897X

Graph transfer learning endeavors to develop a Graph Neural Network (GNN) model in a fully-labeled source domain, with the intention of deploying it on a target domain that has limited labeled data for inference. We reveal that prevalent graph transfer learning methods are susceptible to the homophily shift problem. This issue arises from the divergence in homophily structures between the source and target graphs, leading to a notable deterioration in the performance of GNN models. In this paper, we introduce a novel Contextual Structural Graph Neural Network (CS-GNN) method, leveraging a tailored attention mechanism to apprehend a variety of local structural cues, facilitating structural knowledge transfer across domains. It features an ego-network module to distill local structural diversity and a moment-based approach to gauge structural patterns without needing ground-truth labels. CS-GNN crafts a feature smoothness matrix from node attributes, guiding a customized attention mechanism for feature aggregation. A group-wise fairness loss is employed to balance learning across various structural patterns, enhancing the model’s ability to transfer knowledge across domains. Comprehensive experiments conducted on six benchmark datasets substantiate the superiority of CS-GNN over the state-of-the-art methods, demonstrating significant improvements in accuracy and robustness against homophily shifts. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Unsupervised feature selection via multiple graph fusion and feature weight learning

引用

Science China(Information Sciences) 2023年第5期66卷 56-72页

作者： Chang TANG Xiao ZHENG Wei ZHANG Xinwang LIU Xinzhong ZHU En ZHU School of Computer Science China University of Geosciences State Key Laboratory for Novel Software Technology Nanjing University School of Computer National University of Defense Technology National Supercomputing Center in Jinan Qilu University of Technology (Shandong Academy of Sciences) College of Mathematics Physics and Information Engineering Zhejiang Normal University

Unsupervised feature selection attempts to select a small number of discriminative features from original high-dimensional data and preserve the intrinsic data structure without using data labels. As an unsupervised learning task, most previous methods often use a coefficient matrix for feature reconstruction or feature projection, and a certain similarity graph is widely utilized to regularize the intrinsic structure preservation of original data in a new feature space. However, a similarity graph with poor quality could inevitably afect the final results. In addition, designing a rational and efective feature reconstruction/projection model is not easy. In this paper, we introduce a novel and efective unsupervised feature selection method via multiple graph fusion and feature weight learning（MGF2WL） to address these issues. Instead of learning the feature coefficient matrix, we directly learn the weights of diferent feature dimensions by introducing a feature weight matrix, and the weighted features are projected into the label space. Aiming to exploit sufficient relation of data samples, we develop a graph fusion term to fuse multiple predefined similarity graphs for learning a unified similarity graph, which is then deployed to regularize the local data structure of original data in a projected label space. Finally, we design a block coordinate descent algorithm with a convergence guarantee to solve the resulting optimization problem. Extensive experiments with sufficient analyses on various datasets are conducted to validate the efficacy of our proposed MGF2WL.

关键词： unsupervised feature selection graph fusion feature weight learning local structure preservation

来源：评论

学校读者我要写书评

暂无评论

AE-TPGG:a novel autoencoder-based approach for single-cell RNA-seq data imputation and dimensionality reduction

引用

Frontiers of computer Science 2023年第3期17卷 217-234页

作者： Shuchang ZHAO Li ZHANG Xuejun LIU MIIT Key Laboratory of Pattern Analysis and Machine Intelligence College of Computer Science and TechnologyNanjing University of Aeronautics and AstronauticsNanjing 211106China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing 210023China College of Computer Science and Technology Nanjing Forestry UniversityNanjing 210037China

Single-cell RNA sequencing(scRNA-seq)technology has become an effective tool for high-throughout transcriptomic study,which circumvents the averaging artifacts corresponding to bulk RNA-seq technology,yielding new perspectives on the cellular diversity of potential superficially homogeneous *** various sequencing techniques have decreased the amplification bias and improved capture efficiency caused by the low amount of starting material,the technical noise and biological variation are inevitably introduced into experimental process,resulting in high dropout events,which greatly hinder the downstream *** the bimodal expression pattern and the right-skewed characteristic existed in normalized scRNA-seq data,we propose a customized autoencoder based on a twopart-generalized-gamma distribution(AE-TPGG)for scRNAseq data analysis,which takes mixed discrete-continuous random variables of scRNA-seq data into account using a twopart model and utilizes the generalized gamma(GG)distribution,for fitting the positive and right-skewed continuous *** adopted autoencoder enables AE-TPGG to captures the inherent relationship between *** addition to the ability of achieving low-dimensional representation,the AETPGG model also provides a denoised imputation according to statistical characteristic of gene *** on real datasets demonstrate that our proposed model is competitive to current imputation methods and ameliorates a diverse set of typical scRNA-seq data analyses.

关键词： scRNA-seq autoencoder TPGG data imputation dimensionality reduction

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：