检索结果-内蒙古大学图书馆

Inductive Lottery Ticket Learning for Graph Neural Networks

Journal of computer science & Technology 2024年第6期39卷 1223-1237页

作者： Yong-Duo Sui Xiang Wang Tianlong Chen Meng Wang Xiang-Nan He Tat-Seng Chua School of Data Science University of Science and Technology of ChinaHefei 230027China Department of Electrical and Computer Engineering The University of Texas at AustinAustin 78712U.S.A School of Computer Science and Information Engineering Hefei University of TechnologyHefei 230009China School of Computing National University of SingaporeSingapore

Graph neural networks (GNNs) have gained increasing popularity, while usually suffering from unaffordable computations for real-world large-scale applications. Hence, pruning GNNs is of great need but largely unexplored. The recent work Unified GNN Sparsification (UGS) studies lottery ticket learning for GNNs, aiming to find a subset of model parameters and graph structures that can best maintain the GNN performance. However, it is tailed for the transductive setting, failing to generalize to unseen graphs, which are common in inductive tasks like graph classification. In this work, we propose a simple and effective learning paradigm, Inductive Co-Pruning of GNNs (ICPG), to endow graph lottery tickets with inductive pruning capacity. To prune the input graphs, we design a predictive model to generate importance scores for each edge based on the input. To prune the model parameters, it views the weight’s magnitude as their importance scores. Then we design an iterative co-pruning strategy to trim the graph edges and GNN weights based on their importance scores. Although it might be strikingly simple, ICPG surpasses the existing pruning method and can be universally applicable in both inductive and transductive learning settings. On 10 graph-classification and two node-classification benchmarks, ICPG achieves the same performance level with 14.26%–43.12% sparsity for graphs and 48.80%–91.41% sparsity for the GNN model.

关键词： lottery ticket hypothesis graph neural networks neural network pruning

来源：评论

学校读者我要写书评

暂无评论

MD-HIT:Machine learning for material property prediction with dataset redundancy control

引用

npj Computational Materials 2024年第1期10卷 638-648页

作者： Qin Li Nihang Fu Sadman Sadeed Omee Jianjun Hu College of Big Data and Statistics Guizhou University of Finance and EconomicsGuiyangChina Department of Computer SCience and Engineering University of South CarolinaColumbiaSCUSA

Materials datasets usually contain many redundant(highly similar)materials due to the tinkering approach historically used in material *** redundancy skews the performance evaluation of machine learning(ML)models when using random splitting,leading to overestimated predictive performance and poor performance on out-of-distribution *** issue is well-known in bioinformatics for protein function prediction,where tools like CD-HIT are used to reduce redundancy by ensuring sequence similarity among samples greater than a given *** this paper,we survey the overestimated ML performance in materials science for material property prediction and propose MD-HIT,a redundancy reduction algorithm for material *** MD-HIT to composition-and structure-based formation energy and band gap prediction problems,we demonstrate that with redundancy control,the prediction performances of the ML models on test sets tend to have relatively lower performance compared to the model with high redundancy,but better reflect models’true prediction capability.

关键词： prediction property performance

来源：评论

学校读者我要写书评

暂无评论

Steel Surface Defect Detection Using Learnable Memory Vision Transformer

引用

computers, Materials & Continua 2025年第1期82卷 499-520页

作者： Syed Tasnimul Karim Ayon Farhan Md.Siraj Jia Uddin Department of Computer Science and Engineering BRAC UniversityDhaka1212Bangladesh Department of AI and Big Data Endicott CollegeWoosong UniversityDaejeon34606Republic of Korea

This study investigates the application of Learnable Memory Vision Transformers(LMViT)for detecting metal surface flaws,comparing their performance with traditional CNNs,specifically ResNet18 and ResNet50,as well as other transformer-based models including Token to Token ViT,ViT withoutmemory,and Parallel *** awidely-used steel surface defect dataset,the research applies data augmentation and t-distributed stochastic neighbor embedding(t-SNE)to enhance feature extraction and *** techniques mitigated overfitting,stabilized training,and improved generalization *** LMViT model achieved a test accuracy of 97.22%,significantly outperforming ResNet18(88.89%)and ResNet50(88.90%),aswell as the Token to TokenViT(88.46%),ViT without memory(87.18),and Parallel ViT(91.03%).Furthermore,LMViT exhibited superior training and validation performance,attaining a validation accuracy of 98.2%compared to 91.0%for ResNet 18,96.0%for ResNet50,and 89.12%,87.51%,and 91.21%for Token to Token ViT,ViT without memory,and Parallel ViT,*** findings highlight the LMViT’s ability to capture long-range dependencies in images,an areawhere CNNs struggle due to their reliance on local receptive fields and hierarchical feature *** additional transformer-based models also demonstrate improved performance in capturing complex features over CNNs,with LMViT excelling particularly at detecting subtle and complex defects,which is critical for maintaining product quality and operational efficiency in industrial *** instance,the LMViT model successfully identified fine scratches and minor surface irregularities that CNNs often *** study not only demonstrates LMViT’s potential for real-world defect detection but also underscores the promise of other transformer-based architectures like Token to Token ViT,ViT without memory,and Parallel ViT in industrial scenarios where complex spatial relationships are *** research m

关键词： Learnable Memory Vision Transformer(LMViT) Convolutional Neural Networks(CNN) metal surface defect detection deep learning,computer vision image classification learnable memory gradient clipping label smoothing t-SNE visualization

来源：评论

学校读者我要写书评

暂无评论

Application of the Deep Convolutional Neural Network for the Classification of Auto Immune Diseases

引用

computers, Materials & Continua 2023年第10期77卷 647-664页

作者： Fayaz Muhammad Jahangir Khan Asad Ullah Fasee Ullah Razaullah Khan Inayat Khan Mohammed ElAffendi Gauhar Ali Department of Computer Science and Information Technology Sarhad University of Science and Information TechnologyPeshawar25000Pakistan Department of Computer Science University of Engineering and TechnologyMardan23200Pakistan EIAS Data Science and Blockchain Lab College of Computer and Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia

IIF(Indirect Immune Florescence)has gained much attention recently due to its importance in medical *** primary purpose of this work is to highlight a step-by-step methodology for detecting autoimmune *** use of IIF for detecting autoimmune diseases is widespread in different medical *** 80 different types of autoimmune diseases have existed in various body *** IIF has been used for image classification in both ways,manually and by using the computer-Aided Detection(CAD)*** data scientists conducted various research works using an automatic CAD system with low *** diseases in the human body can be detected with the help of Transfer Learning(TL),an advanced Convolutional Neural Network(CNN)*** baseline paper applied the manual classification to the MIVIA dataset of Human Epithelial cells(HEP)type II cells and the Sub Class Discriminant(SDA)analysis technique used to detect autoimmune *** technique yielded an accuracy of up to 90.03%,which was not reliable for detecting autoimmune disease in the mitotic cells of the *** the current research,the work has been performed on the MIVIA data set of HEP type II cells by using four well-known models of *** augmentation and normalization have been applied to the dataset to overcome the problem of overfitting and are also used to improve the performance of TL *** models are named Inception V3,Dens Net 121,VGG-16,and Mobile Net,and their performance can be calculated through parameters of the confusion matrix(accuracy,precision,recall,and F1 measures).The results show that the accuracy value of VGG-16 is 78.00%,Inception V3 is 92.00%,Dense Net 121 is 95.00%,and Mobile Net shows 88.00%accuracy,***,DenseNet-121 shows the highest performance with suitable analysis of autoimmune *** overall performance highlighted that TL is a suitable and enhanced technique compared to its ***,the proposed technique is used

关键词： Indirect immune fluorescence computer-aided diagnosis transfer learning confusion matrix

来源：评论

学校读者我要写书评

暂无评论

SMT-PREDICT: An Efficient Framework for Stock Market Trend Prediction using Historical and Sentimental data 3

SMT-PREDICT: An Efficient Framework for Stock Market Trend P...

引用

3rd International Conference for Advancement in Technology, ICONAT 2024

作者： Raju, Abhijith Arun, K. Sudha, S.K. Aji, S. University of Kerala Department of Computer Science Kerala India University of Kerala Centre for Data Science and Information Processing Department of Computer Science Kerala India

ISBN: (纸本)9798350354171

Predicting stock market trends is vital due to its economic impact and benefits. In global finance, stock movements are influenced by numerous factors, especially news and sentiment. High volatility, driven by political, economic, leadership changes, and investor sentiment, makes stock prices hard to predict. Solely relying on historical data or textual information for predictions has proven insufficient. Hence, this paper proposes an efficient framework using Sentiment Polarity Inscribed Deep Features (SPIDF). Deep features are extracted from historical stock data using a Denoising Autoencoder (DAE), while the Sentiment Polarity Index (SPI) is derived from news headlines to generate SPIDF. The robust SPIDF is then used to predict stock market trends (SMT-Predict) with a Bi-Long Short-Term Memory (BiLSTM) network. The results demonstrate that the SMT-Predict model effectively incorporates SPIDF with essential Financial Indicators (FI) for accurate stock market trend prediction. © 2024 IEEE.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

Enhancing Fetal Care and Maternal Health with Machine Learning: A Systematic Review

Enhancing Fetal Care and Maternal Health with Machine Learni...

引用

2024 IEEE International Conference on Intelligent Computing and Emerging Communication Technologies, ICEC 2024

作者： Puri, Chetan Reddy, K.T.V. Department of Computer Science and Design Wardha India Department of Artificial Intelligence and Data Science Wardha India

ISBN: (纸本)9798331508432

Fetal growth restriction and preterm delivery proceed to be major around the world wellbeing concerns, with serious consequences for the wellbeing of moms and babies. Provoke and exact estimating of these issues is basic for prompt action. In spite of the fact that progresses have been made in conventional clinical assessment approaches, the potential of computational apparatuses to back clinical decision-making is getting to be progressively clear. With its capacity to assess complex data patterns, machine learning (ML) has gotten to be a reasonable procedure for making strides pre-birth care. The review's conclusions highlight ML's potential to upgrade fetal care. Various examinations yielded empowering discoveries, as machine learning models outperformed routine risk evaluation instruments in terms of anticipated exactness. Numerous pregnancy issues, counting fetal growth limitation and untimely conveyance, have been viably anticipated by machine learning calculations. Healthcare experts can reduce unfavorable results by utilizing focused medicines to distinguish high-risk pregnancies early on. In any case, obstacles and confinements anticipate machine learning from being broadly utilized in restorative settings. Given that solid machine learning models require expansive and representative datasets, information accessibility and quality stay significant concerns. It is vital to ensure information security and take moral issues into consideration. Besides, ML models regularly have destitute interpretability, which makes it challenging to comprehend the basic components directing predictions. Future considers ought to concentrate on making and assessing machine learning models over a extend of demographics, improving the interpretability of models, and incorporating ML into clinical strategies. By handling these issues, machine learning (ML) has the potential to make strides the wellbeing of expectant women and their babies. © 2024 IEEE.

关键词： Obstetrics

来源：评论

学校读者我要写书评

暂无评论

Improving Group Robustness on Spurious Correlation Requires Preciser Group Inference 41

Improving Group Robustness on Spurious Correlation Requires ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Han, Yujin Zou, Difan Department of Computer Science The University of Hong Kong Hong Kong Department of Computer Science Institute of Data Science The University of Hong Kong Hong Kong

Standard empirical risk minimization (ERM) models may prioritize learning spurious correlations between spurious features and true labels, leading to poor accuracy on groups where these correlations do not hold. Mitigating this issue often requires expensive spurious attribute (group) labels or relies on trained ERM models to infer group labels when group information is unavailable. However, the significant performance gap in worst-group accuracy between using pseudo group labels and using oracle group labels inspires us to consider further improving group robustness through preciser group inference. Therefore, we propose GIC, a novel method that accurately infers group labels, resulting in improved worst-group performance. GIC trains a spurious attribute classifier based on two key properties of spurious correlations: (1) high correlation between spurious attributes and true labels, and (2) variability in this correlation between datasets with different group distributions. Empirical studies on multiple datasets demonstrate the effectiveness of GIC in inferring group labels, and combining GIC with various downstream invariant learning methods improves worst-group accuracy, showcasing its powerful flexibility. Additionally, through analyzing the misclassifications in GIC, we identify an interesting phenomenon called semantic consistency, which may contribute to better decoupling the association between spurious attributes and labels, thereby mitigating spurious correlation. The code for GIC is available at https://***/yujinhanml/GIC. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Immersive video interaction system: a survey

引用

Visual Intelligence 2025年第1期3卷 1-14页

作者： Fang, Xiaohan Chen, Peilin Wang, Meng Wang, Shiqi Department of Computer Science City University of Hong Kong Hong Kong School of Data Science Lingnan University Hong Kong

As communication technologies undergo rapid evolution, human interaction technologies have become increasingly efficient and accessible. Videoconferencing, for example, facilitates real-time, face-to-face communication worldwide, providing unprecedented convenience. Nevertheless, traditional two-dimensional (2D) videoconferencing systems frequently fall short of delivering a fully immersive experience, as they lack the ability to convey physical presence, depth perception, and natural interaction—key elements that are of particular significance in replicating the subtleties inherent in in-person communication. This disconnection leaves users yearning for the rich, multi-sensory experiences that real-life interactions can offer. In response, significant research efforts have been dedicated to the development of immersive video interaction systems (IVISs). This paper introduces the concept of IVISs and reviews a spectrum of systems advanced by researchers and industry innovators, each of whom contributes unique insights into the evolution of this field. A comparative analysis of the characteristics of current IVISs is provided, offering insights across multiple dimensions. This survey concludes with a discussion of potential future research directions and the challenges that remain in enhancing the IVIS technology. Through a comprehensive analysis, this work aims to foster further exploration and innovation in immersive communication technologies. © The Author(s) 2025.

关键词： 3D vision Immersive video interaction systems Survey Video communication

来源：评论

学校读者我要写书评

暂无评论

Age-of-Information-Aware Federated Learning

引用

Journal of computer science & Technology 2024年第3期39卷 637-653页

作者：徐殷肖明军吴晨吴杰周津锐孙贺 Student Member CCF 1.School of Computer Science and TechnologyUniversity of Science and Technology of ChinaHefei 230026China Suzhou Institute for Advanced Research University of Science and Technology of ChinaSuzhou 215123China School of Data Science University of Science and Technology of ChinaHefei 230026China Department of Computer and Information Sciences Temple UniversityPhiladelphiaPA 19122U.S.A. CCF IEEE

Federated learning(FL)is an emerging privacy-preserving distributed computing paradigm,enabling numerous clients to collaboratively train machine learning models without the necessity of transmitting clients’private datasets to the central *** most existing research where the local datasets of clients are assumed to be unchanged over time throughout the whole FL process,our study addresses such scenarios in this paper where clients’datasets need to be updated periodically,and the server can incentivize clients to employ as fresh as possible datasets for local model *** primary objective is to design a client selection strategy to minimize the loss of the global model for FL loss within a constrained *** this end,we introduce the concept of“Age of Information”(AoI)to quantitatively assess the freshness of local datasets and conduct a theoretical analysis of the convergence bound in our AoI-aware FL *** on the convergence bound,we further formulate our problem as a restless multi-armed bandit(RMAB)***,we relax the RMAB problem and apply the Lagrangian Dual approach to decouple it into multiple ***,we propose a Whittle’s Index Based Client Selection(WICS)algorithm to determine the set of selected *** addition,comprehensive simulations substantiate that the proposed algorithm can effectively reduce training loss and enhance the learning accuracy compared with some state-of-the-art methods.

关键词： federated learning Age of Information restless multi-armed bandit Whittle’s index

来源：评论

学校读者我要写书评

暂无评论

ETiSeg-Net: edge-aware self attention to enhance tissue segmentation in histopathological images

引用

Multimedia Tools and Applications 2024年 1-21页

作者： Rashmi, R. Girisha, S. Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Data Science and Computer Applications Manipal Institute of Technology Manipal Academy of Higher Education Manipal India

Digital pathology employing Whole Slide Images (WSIs) plays a pivotal role in cancer detection. Nevertheless, the manual examination of WSIs for the identification of various tissue regions presents formidable challenges due to its labor-intensive nature and subjective interpretation. Convolutional Neural Network (CNN) based semantic segmentation algorithms have emerged as valuable tools for assisting in this task by automating ROI delineation. The incorporation of attention modules and carefully designed loss functions has shown promise in further augmenting the performance of these algorithms. However, there exists a notable gap in research regarding the utilization of attention modules specifically for tissue segmentation, thereby constraining our comprehension and application of these modules in this context. This study introduces ETiSeg-Net (Edge-aware self attention to enhance Tissue Segmentation), a CNN-based semantic segmentation model that uses a novel edge-based attention module to achieve effective delineation of class boundaries. In addition, an innovative iterative training strategy is devised to efficiently optimize the model parameters. The study also conducts a comprehensive investigation into the impact of attention modules and loss functions on the efficacy of semantic segmentation models. Qualitative and quantitative evaluations of these semantic segmentation models are conducted using publicly available datasets. The findings underscore the potential of attention modules in enhancing the accuracy and effectiveness of tissue semantic segmentation. © The Author(s) 2024.

关键词： Semantic Segmentation

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：