检索结果-内蒙古大学图书馆

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Li, Zhi Wu, Bo Liu, Qi Wu, Likang Zhao, Hongke Mei, Tao Anhui Province Key Laboratory of Big Data Analysis and Application School of Data Science University of Science and Technology of China China Columbia University United States School of Computer Science and Technology University of Science and Technology of China China College of Management and Economics Tianjin University China JD AI Research

ISBN: (纸本)9780999241165

Complementary recommendations, which aim at providing users product suggestions that are supplementary and compatible with their obtained items, have become a hot topic in both academia and industry in recent years. Existing work mainly focused on modeling the co-purchased relations between two items, but the compositional associations of item collections are largely unexplored. Actually, when a user chooses the complementary items for the purchased products, it is intuitive that she will consider the visual semantic coherence (such as color collocations, texture compatibilities) in addition to global impressions. Towards this end, in this paper, we propose a novel Content Attentive Neural Networks (CANN) to model the comprehensive compositional coherence on both global contents and semantic contents. Specifically, we first propose a Global Coherence Learning (GCL) module based on multi-heads attention to model the global compositional coherence. Then, we generate the semantic-focal representations from different semantic regions and design a Focal Coherence Learning (FCL) module to learn the focal compositional coherence from different semantic-focal representations. Finally, we optimize the CANN in a novel compositional optimization strategy. Extensive experiments on the large-scale real-world data clearly demonstrate the effectiveness of CANN compared with several state-of-the-art methods. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Path-aware multi-scale learning for heterogeneous graph neural network

引用

Neural Networks 2025年 191卷

作者： Jin Fan Jiajun Yang Zhangyu Gu Huifeng Wu Danfeng Sun Feiwei Qin Jia Wu Department of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Zhejiang Key Laboratory of New Industrial Internet Control Technology Hangzhou Dianzi University Hangzhou China Laboratory of Intelligent Education Technology and Application of Zhejiang Province Zhejiang Normal University Hangzhou China Department of Computing Macquarie University Sydney Australia

Heterogeneous Graph Neural Networks (HGNNs) are a powerful tool for modeling data with diverse node and edge types, found in applications like social networks, recommendation systems, and knowledge graphs, including tasks such as node classification, link prediction, and graph classification. Based on information aggregation methods, HGNNs can be broadly categorized into meta-path-free and meta-path-based HGNNs. Recently, meta-path-based HGNNs have made significant advancements in both performance and interpretability. However, these methods often overlook the redundancy among meta-paths and fail to fully leverage the inherent information within the paths, such as path length and path type. Furthermore, their insufficient utilization of global information hinders comprehensive representation learning. To address these issues, we propose a path-aware multi-scale heterogeneous graph neural network named PM-HGNN. To better capture global information, PM-HGNN employs a global similarity-based mean aggregator to pre-compute neighbor aggregation information. Additionally, PM-HGNN exploits the inherent relevance and differences between meta-paths, enabling redundancy reduction and the dynamic assignment of weights. Experiments conducted on four real-world heterogeneous graph datasets revealed that PM-HGNN consistently exceeds the performance of current state-of-the-art methods in tasks related to node classification.

关键词：

来源：评论

学校读者我要写书评

暂无评论

XCrossNet: Feature structure-oriented learning for click-through rate prediction

arXiv

引用

arXiv 2021年

作者： Yu, Runlong Ye, Yuyang Liu, Qi Wang, Zihan Yang, Chunfeng Hu, Yucheng Chen, Enhong Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China Hefei China Management Science and Information Systems Rutgers Business School Rutgers University Newark United States MOE Key Laboratory of Computational Linguistics School of Electronics Engineering and Computer Science Peking University Beijing China Tencent Inc Shenzhen China

Click-Through Rate (CTR) prediction is a core task in nowadays commercial recommender systems. Feature crossing, as the mainline of research on CTR prediction, has shown a promising way to enhance predictive performance. Even though various models are able to learn feature interactions without manual feature engineering, they rarely attempt to individually learn representations for different feature structures. In particular, they mainly focus on the modeling of cross sparse features but neglect to specifically represent cross dense features. Motivated by this, we propose a novel Extreme Cross Network, abbreviated XCrossNet, which aims at learning dense and sparse feature interactions in an explicit manner. XCrossNet as a feature structure-oriented model leads to a more expressive representation and a more precise CTR prediction, which is not only explicit and interpretable, but also time-efficient and easy to implement. Experimental studies on Criteo Kaggle dataset show significant improvement of XCrossNet over state-of-the-art models on both effectiveness and efficiency. © 2021, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Mccseg: Morphological Guided Causal Constraint Network for Medical Image Multi-Object Segmentation

SSRN

引用

SSRN 2023年

作者： Gao, Yifan Wei, Lifang Li, Jun Chang, Xinyue Zhang, Yulong Chen, Riqing Yang, Changcai Wei, Yi Dong, Heng Digital Fujian Research Institute of Big Data for Agriculture and Forestry College of Computer and Information Science Fujian Agriculture and Forestry University Fuzhou350002 China Institute for AI in Medicine School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing210000 China Department of Obstetrics & Gynecology College of Clinical Medicine for Obstetrics & Gynecology and Pediatrics Fujian Medical University Fuzhou350001 China School of Mathematics and Computer Science Fujian Key Laboratory of Big Data Application and Intellectualization for Tea Industry Wuyi University Fujian354300 China

Medical image multi-object segmentation aims to accurately extract each object that is great significance for the medical image analysis. Although several methods based on deep leaning have been widely developed, it is still challenging due to the similarities of different objects, the significant variability of morphology, data heterogeneity and the unbalanced distribution of samples. To address the above issues, we propose a novel Morphological Guided Causal Constraint segmentation network (MCCSeg) for medical image multi-object segmentation. We build a hybrid CNN-Transformer encoder module to obtain local and global features. Specifically, a Causal Constraint Module (CCM) is proposed for feature decorrelation by sample reweighting, which utilizes weight allocation to train the weight of training samples. The Random Fourier Features (RFF) are used to solve nonlinear dependency problems and remove correlations between features for eliminating the impact of spurious correlations. The morphological guidance module (MG) is designed to extract the boundary as prior morphology information for enhancing feature representation, which are concatenated into the deep supervision module in decoder for further optimizing feature extraction. The experiments demonstrate that MCCSeg outperforms other state-of-the-art methods, obtaining up 3.76% and 5.41% improvements in DICE and HD95 scores on Synapse dataset, respectively. And the ablation experiments further verify the effectiveness of MCCSeg in improving generalization. The source code will be released at https://***/YfGAO/MCCSeg. © 2023, The Authors. All rights reserved.

关键词： Morphology

来源：评论

学校读者我要写书评

暂无评论

Lesionmix Data Enhancement and Entropy Minimization for Semi-Supervised Lesion Segmentation of Lung Cancer

SSRN

引用

SSRN 2024年

作者： Pan, Xipeng Chen, Mingwei Lin, Huan Bian, Xinjun Feng, Siyang Chen, Jiale Wang, Lin Chen, Xin Liu, Zaiyi Lan, Rushi School of Computer Science and Information Security Guilin University of Electronic Technology Guangxi Guilin541004 China Department of Radiology Guangdong Provincial People’s Hospital Guangdong Academy of Medical Sciences Southern Medical University Guangzhou510080 China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangdong Provincial People’s Hospital Guangdong Academy of Medical Sciences Guangdong Guangzhou510080 China State Key Laboratory of Oncology in South China Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy Guangdong Provincial Clinical Research Center for Cancer Sun Yat-sen University Cancer Center Guangzhou510060 China Department of Nasopharyngeal Carcinoma Sun Yat-sen University Cancer Center Guangzhou510060 China Department of Radiology Guangzhou First People’s Hospital School of Medicine South China University of Technology Guangdong Guangzhou510180 China Guangdong Provincial People's Hospital China School of Medicine China

Determining the location and contour of the lesion is an important prerequisite for medical diagnosis, subsequent personalized treatment plan and prognostic prediction. Semi-supervised learning and data enhancement methods facilitate deep learning to be used in many fields of medical imaging. In this paper, we propose a data enhancement method named LesionMix, which performs lesion extraction and reuses through a small amount of labeled CT data to improve the utilization efficiency of the labeled data. Meanwhile, we propose a two-stage semi-supervised training strategy called Entropy Minimization LesionMix, in which features containing lesion contour information are quickly learned through LesionMix data augmentation in the first stage. Entropy minimization strategy optimizes the model parameters to alleviate overfitting as much as possible in the second stage and improves prediction confidence. Our proposed method is validated on an public LIDC-IDRI dataset and an in-house GDPHLUAD dataset. Extensive experiments demonstrate that our method achieves promising performance and outperforms seven state-of-the-art semi-supervised models;Moreover, ablation experiments validate the effectiveness of various aspects of our approach. © 2024, The Authors. All rights reserved.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Morphological Guided Causal Constraint Network for Medical Image Multi-Object Segmentation

Morphological Guided Causal Constraint Network for Medical I...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yifan Gao Jun Li Xinyue Chang Yulong Zhang Riqing Chen Changcai Yang Yi Wei Heng Dong Lifang Wei College of Computer and Information Science Fujian Agriculture and Forestry University Fujian China Institute for AI in Medicine School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing China College of Clinical Medicine for Obstetrics & Gynecology and Pediatrics Fujian Medical University Fujian China Digital Fujian Research Institute of Big Data for Agriculture and Forestry Fujian Agriculture and Forestry University Fujian China School of Mathematics and Computer Science Fujian Key Laboratory of Big Data Application and Intellectualization for Tea Industry Wuyi University Fujian China

Multi-objective segmentation (MOS) in medical images is to simultaneously extract multiple regions of interest in the medical images. Due to the unbalanced distribution of samples and the similarity and significant differences between features in medical images, current methods still struggle to achieve satisfactory results. In this context, we propose a novel Morphological Guided Causal Constrain segmentation network (MCCSeg) for medical image multi-object segmentation. We introduced a Causal Constrain Module (CCM) for feature decorrelation by sample reweighting. The morphological guidance module (MG) is designed to extract the boundary features as the prior shape information for enhancing feature representation. Our experiments demonstrate that MCCSeg outperforms other state-of-the-art methods, obtaining up 3.76% and 5.41% improvements in DICE and HD95 scores on Synapse dataset, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Reconstruction Method for Cross-Cut Shredded Documents Based on the Extreme Learning Machine Algorithm

Research Square

引用

Research Square 2022年

作者： Zhang, Zhenghui Zou, Juan Zheng, Jinhua Yang, Shengxiang Gong, Dunwei Pei, Tingrui Key Laboratory of Hunan Province for Internet of Things and Information Security Xiangtan University Hunan Xiangtan411105 China Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Information Engineering College of Xiangtan University Hunan Xiangtan411105 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang421002 China School of Computer Science and Informatics De Montfort University LeicesterLE1 9BH United Kingdom School of Information and Electronic Engineering China University of Mining and Technology Xuzhou221116 China

Reconstruction of cross-cut shredded text documents (RCCSTD) has important applications for information security and judicial evidence collection. The traditional method of manual construction is a very time-consuming task, so the use of computer-assisted efficient reconstruction is a crucial research topic. Fragment consensus information extraction and fragment pair compatibility measurement are two fundamental processes in RCCSTD. Due to the limitations of the existing classical methods of these two steps, only documents with specific structures or characteristics can be spliced, and pairing error is larger when the cutting is more fine-grained. In order to reconstruct the fragments more effectively, this paper improves the extraction method for consensus information and constructs a new global pairwise compatibility measurement model based on the extreme learning machine algorithm. The purpose of the algorithm’s design is to exploit all available information and computationally suggest matches to increase the algorithm’s ability to discriminate between data in various complex situations, then find the best neighbor of each fragment for splicing according to pairwise compatibility. The overall performance of our approach in several practical experiments is illustrated. The results indicate that the matching accuracy of the proposed algorithm is better than that of the previously published classical algorithms and still ensures a higher matching accuracy in the noisy datasets, which can provide a feasible method for RCCSTD intelligent systems in real scenarios. © 2022, CC BY.

关键词： Knowledge acquisition

来源：评论

学校读者我要写书评

暂无评论

Boosting Factorization Machines via Saliency-Guided Mixup

arXiv

引用

arXiv 2022年

作者： Wu, Chenwang Lian, Defu Ge, Yong Zhou, Min Chen, Enhong Tao, Dacheng School of Data Science University of Science and Technology of China Anhui Hefei230000 China Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China Anhui Hefei230000 China Eller College of Management University of Arizona United States Huawei Noah’s Ark Lab Hong Kong JD Explore Academy in *** China University of Sydney Australia

Factorization machines (FMs) are widely used in recommender systems due to their adaptability and ability to learn from sparse data. However, for the ubiquitous non-interactive features in sparse data, existing FMs can only estimate the parameters corresponding to these features via the inner product of their embeddings. Undeniably, they cannot learn the direct interactions of these features, which limits the model’s expressive power. To this end, we first present MixFM, inspired by Mixup, to generate auxiliary training data to boost FMs. Unlike existing augmentation strategies that require labor costs and expertise to collect additional information such as position and fields, these extra data generated by MixFM only by the convex combination of the raw ones without any professional knowledge support. More importantly, if the parent samples to be mixed have non-interactive features, MixFM will establish their direct interactions. Second, considering that MixFM may generate redundant or even detrimental instances, we further put forward a novel Factorization Machine powered by Saliency-guided Mixup (denoted as SMFM). Guided by the customized saliency, SMFM can generate more informative neighbor data. Through theoretical analysis, we prove that the proposed methods minimize the upper bound of the generalization error, which hold a beneficial effect on enhancing FMs. Significantly, we give the first generalization bound of FM, implying the generalization requires more data and a smaller embedding size under the sufficient representation capability. Finally, extensive experiments on five datasets confirm that our approaches are superior to baselines. Besides, the results show that"poisoning" mixed data is likewise beneficial to the FM variants. Copyright © 2022, The Authors. All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Automatic Fault Diagnosis of Smart Water Meter Based on BP Neural Network 1

引用

6th International Conference of Pioneering computer Scientists, Engineers and Educators, ICPCSEE 2020

作者： Lin, Jing Mi, Chunqiao School of Computer Science and Engineering Huaihua University HuaihuaHunan418000 China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing and Application in Hunan Province Universities HuaihuaHunan418000 China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province HuaihuaHunan418000 China

ISBN: (数字)9789811579844

ISBN: (纸本)9789811579837

The smart water meter in water supply network can directly affect water production and usage when faults occur. The traditional method of fault detection is inefficient with time lagging, which is not helpful for modernization of water supply system. The capability of automatic fault diagnosis of smart water meter is an important means to improve the service quality of water supply. In this paper, an automatic fault diagnosis method for the smart device is proposed based on BP neural network. And it was applied on Google Tensorflow platform. Fault symptom vectors were constructed using water meter status data and were used to train the neural network model. In order to improve the learning convergence speed and fault classification effect of the network, a method of weighted symptom was also employed. Experimental results show that it has good performance with a general fault diagnosis accuracy of 98.82%. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

A Image Adaptive Steganography Algorithm Combining Chaotic Encryption and Minimum Distortion Function

A Image Adaptive Steganography Algorithm Combining Chaotic E...

引用

作者： Ge Jiao Jiahao Liu Sheng Zhou Ning Luo College of Computer Science and Technology Hengyang Normal University Hunan Provincial Key Laboratory of Intelligent Information Processing and Application

Digital image has the characteristics of high redundancy and convenient processing, which is the ideal carrier of information hiding ***, digital image steganography has become a hot research direction in the field of information security. In order to ensure the concealment, reliability and security of image steganographic information, an image adaptive steganographic algorithm combining chaotic encryption and minimum distortion function is designed. The algorithm generates random keys, encrypt the secret information using Logistic and ChebyShev mapping, and then embeds the key and the encrypted secret information into the carrier image using the HILL steganographic algorithm. The algorithm stores the embedded key and the decryption key separately, so the attacker cannot get the correct secret information even if he gets the embedded key, which improves the security of the key. Experiments show that the pixel change rate of the algorithm is 6.76%, the peak signal-to-noise ratio is 59.51 db, and it has a very good anti-steganographic analysis ability.

关键词： Image adaptive steganography Chaotic encryption Cost PSNR

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：