检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Yao, Zhen Zhang, Wen Chen, Mingyang Huang, Yufeng Yang, Yi Chen, Huajun School of Software Technology Zhejiang University China College of Computer Science and Technology Zhejiang University China Donghai Laboratory Zhoushan316021 China Huawei Technologies Co. Ltd China Alibaba-Zhejiang University Joint Institute of Frontier Technologies China

Knowledge graph embedding (KGE), which maps entities and relations in a knowledge graph into continuous vector spaces, has achieved great success in predicting missing links in knowledge graphs. However, knowledge graphs often contain incomplete triples that are difficult to inductively infer by KGEs. To address this challenge, we resort to analogical inference and propose a novel and general self-supervised framework AnKGE to enhance KGE models with analogical inference capability. We propose an analogical object retriever that retrieves appropriate analogical objects from entity-level, relation-level, and triple-level. And in AnKGE, we train an analogy function for each level of analogical inference with the original element embedding from a well-trained KGE model as input, which outputs the analogical object embedding. In order to combine inductive inference capability from the original KGE model and analogical inference capability enhanced by AnKGE, we interpolate the analogy score with the base model score and introduce the adaptive weights in the score function for prediction. Through extensive experiments on FB15k-237 and WN18RR datasets, we show that AnKGE achieves competitive results on link prediction task and well performs analogical inference. Copyright © 2023, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Recent advances in artificial intelligence for retrosynthesis

arXiv

引用

arXiv 2023年

作者： Zhong, Zipeng Song, Jie Feng, Zunlei Liu, Tiantao Jia, Lingxiang Yao, Shaolun Hou, Tingjun Song, Mingli College of Computer Science and Technology Zhejiang University Zhejiang310027 China School of Software Technology Zhejiang University Zhejiang315048 China Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University College of Pharmaceutical Sciences Zhejiang University Zhejiang310058 China

Retrosynthesis is the cornerstone of organic chemistry, providing chemists in material and drug manufacturing access to poorly available and brand-new molecules. Conventional rule-based or expert-based computer-aided synthesis has obvious limitations, such as high labor costs and limited search space. In recent years, dramatic breakthroughs driven by artificial intelligence have revolutionized retrosynthesis. Here we aim to present a comprehensive review of recent advances in AI-based retrosynthesis. For single-step and multi-step retrosynthesis both, we first list their goal and provide a thorough taxonomy of existing methods. Afterwards, we analyze these methods in terms of their mechanism and performance, and introduce popular evaluation metrics for them, in which we also provide a detailed comparison among representative methods on several public datasets. In the next part we introduce popular databases and established platforms for retrosynthesis. Finally, this review concludes with a discussion about promising research directions in this field. © 2023, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Sowmark: Neural Networks Copyright Protection Based on Structural Orthogonal Watermarking

SSRN

引用

SSRN 2024年

作者： Chen, Xianyi Hui, Mi Xu, Huiguang He, Junjie Engineering Research Center of Digital Forensics Ministry of Education Nanjing University of Information Science and Technology No.219 Ningliu Road Pukou District Nanjing210044 China School of Computer Science Nanjing University of Information Science and Technology No.219 Ningliu Road Pukou District Nanjing210044 China School of Software Nanjing University of Information Science and Technology No.219 Ningliu Road Pukou District Nanjing210044 China NARI Group Corporation State Grid Electric Power Research Institute Nanjing211106 China

A well-trained deep learning model usually consumes a lot of time and computational resources. However, it is vulnerable to infringement as a digital achievement once published. Recently, many impressive works have emerged for deep model copyright protection. They primarily embed watermarks by modifying model parameters or training samples, which can easily lead to model performance degradation. To this end, we propose a new structure-based DNN orthogonal watermarking method, in which the output features of the orthogonal layer are restricted to be parallel or orthogonal to each other by imposing forward constraint rules. It improves the correlation between the watermark and the model parameters, which improves the feature diversity and enables the model's watermark to effectively resist parameter-based attacks, thus improving the overall performance of the model. Extensive experiments have demonstrated that, the proposed scheme has great fidelity and robustness against various watermark removal attacks, such as parameter fine-tuning and model pruning. © 2024, The Authors. All rights reserved.

关键词： Watermarking

来源：评论

学校读者我要写书评

暂无评论

MrTF: Model Refinery for Transductive Federated Learning

arXiv

引用

arXiv 2023年

作者： Li, Xin-Chun Yang, Yang Zhan, De-Chuan State Key Laboratory for Novel Software Technology Nanjing University Jiangsu Nanjing210023 China School of Artificial Intelligence Nanjing University Jiangsu Nanjing210023 China School of Computer Science and Engineering Nanjing University of Science and Technology Jiangsu Nanjing210094 China Department of Computing The Hong Kong Polytechnic University 100872 Hong Kong

We consider a real-world scenario in which a newly-established pilot project needs to make inferences for newly-collected data with the help of other parties under privacy protection policies. Current federated learning (FL) paradigms are devoted to solving the data heterogeneity problem without considering the to-be-inferred data. We propose a novel learning paradigm named transductive federated learning (TFL) to simultaneously consider the structural information of the to-be-inferred data. On the one hand, the server could use the pre-available test samples to refine the aggregated models for robust model fusion, which tackles the data heterogeneity problem in FL. On the other hand, the refinery process incorporates test samples into training and could generate better predictions in a transductive manner. We propose several techniques including stabilized teachers, rectified distillation, and clustered label refinery to facilitate the model refinery process. Abundant experimental studies verify the superiorities of the proposed Model refinery framework for Transductive Federated learning (MrTF). The source code is available at https://***/lxcnju/MrTF. © 2023, CC BY-NC-ND.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Class-aware Variational Auto-encoder for Open Set Recognition

Class-aware Variational Auto-encoder for Open Set Recognitio...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Ruofan Wang Jiayu Guo Rui-Wei Zhao Ling Su Yingzi Ye Xiaobo Zhang Yuejie Zhang Rui Feng Software School Fudan University Shanghai China Academy for Engineering and Technology Fudan University Shanghai China National Children's Medical Center Children's Hospital of Fudan University Shanghai China School of Computer Science Fudan University Shanghai China

Compared with traditional classification models trained under the closed world assumption, Open Set Recognition (OSR) requires accurate classification for known classes as well as rejection for unknown ones. By modeling the distribution of each known class, Conditional Variational Auto-encoder (CVAE) has achieved great success in OSR, even though it was originally proposed for image generation. In this paper, we propose a novel two-stage learning framework, Class-aware Variational Auto-encoder (CA-VAE) to better adapt CVAE to the OSR task. Pre-derived attention images are taken as the objective target for reconstruction, thus model is implicitly directed to focus on the class-discriminative regions of the image. In this way, the learned latent representation is de-biased towards class-aware. Experiments on standard image datasets demonstrate the outperformance of the proposed method over existing ones, which achieves new state-of-the-art results. Codes are available at https://***/roywang021/CA-VAE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Approach to Segment the Liver Cancer using Machine Learning Method 4

An Intelligent Approach to Segment the Liver Cancer using Ma...

引用

4th International Conference on Electronics and Sustainable Communication Systems, ICESC 2023

作者： Anand, L. Maurya, Mahesh Seetha, J. Nagaraju, D. Ravuri, Ananda Vidhya, R.G. School of Computing Srm Institute of Science and Technology Department of Networking and Communications India University of Mumbai K. C. College of Engineering Management and Research Mith Bunder Road Near Hume Pipe Maharashtra Thane400603 India Panimalar Engineering College Department of Computer Science and Business Systems Chennai India Sri Venkatesa Perumal College of Engineering and Technology Department of CSE Andhra Pradesh Puttur India Senior Software Engineer Intel Corporation HillsboroOR97124 United States Hkbk College of Engineering Department of Ece Bangalore India

ISBN: (纸本)9798350300093

Cancer Liver cancer is difficult to detect and diagnose early. Machine learning has improved liver cancer diagnosis in recent years. This abstract describes a novel liver cancer detection and classification method using Autoencoder-Extreme Learning Machine (AE-ELM) and Convolutional Neural Network (CNN) technology. AE-ELM models extract features in the suggested method. The autoencoder-extreme learning machine AE-ELM technique learns high-level abstract characteristics from incoming data. AE-ELM extracts liver cancer-specific features by reducing the dimensionality of input data. A CNN model classifies the extracted features. CNNs are good at detecting spatial patterns in medical pictures like CT and MRI scans. The CNN model learns hierarchical representations of input information and classifies them into liver cancer subtypes or stages using various convolutional and pooling processes. AE-ELM and CNN are advantageous. First, AE-ELM decreases input data dimensionality to extract critical features without manual feature engineering. This simplifies feature selection and improves the model's capacity to handle big data. Second, the CNN model uses hierarchical convolutional processes to capture subtle patterns and spatial correlations in input data, enhancing liver cancer classification accuracy. The proposed liver cancer diagnostic method works in experiments. AE-ELM and CNN models outperform classic machine learning approaches and standalone CNN models. Improved liver cancer detection accuracy, sensitivity, and specificity help healthcare practitioners make quick and precise diagnosis. Finally, AE-ELM and CNN technologies can identify and classify liver cancer. This unique strategy uses both models to extract relevant characteristics and capture complicated patterns, improving liver cancer diagnosis accuracy and efficiency. To evaluate this approach's therapeutic promise and application in real-world healthcare settings, additional datasets are needed. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep 3D reconstruction:methods,data,and challenges

引用

Frontiers of Information technology & Electronic Engineering 2021年第5期22卷 652-672页

作者： Caixia LIU Dehui KONG Shaofan WANG Zhiyong WANG Jinghua LI Baocai YIN Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing Institute of Artificial IntelligenceFaculty of Information TechnologyBeijing University of TechnologyBeijing 100124China Multimedia Laboratory School of Computer ScienceUniversity of SydneySydney NSW 2006Australia

Three-dimensional(3D)reconstruction of shapes is an important research topic in the fields of computer vision,computer graphics,pattern recognition,and virtual *** 3D reconstruction methods usually suffer from two bottlenecks:(1)they involve multiple manually designed states which can lead to cumulative errors,but can hardly learn semantic features of 3D shapes automatically;(2)they depend heavily on the content and quality of images,as well as precisely calibrated *** a result,it is difficult to improve the reconstruction accuracy of those methods.3D reconstruction methods based on deep learning overcome both of these bottlenecks by automatically learning semantic features of 3D shapes from low-quality images using deep ***,while these methods have various architectures,in-depth analysis and comparisons of them are unavailable so *** present a comprehensive survey of 3D reconstruction methods based on deep ***,based on different deep learning model architectures,we divide 3D reconstruction methods based on deep learning into four types,recurrent neural network,deep autoencoder,generative adversarial network,and convolutional neural network based methods,and analyze the corresponding methodologies ***,we investigate four representative databases that are commonly used by the above methods in ***,we give a comprehensive comparison of 3D reconstruction methods based on deep learning,which consists of the results of different methods with respect to the same database,the results of each method with respect to different databases,and the robustness of each method with respect to the number of ***,we discuss future development of 3D reconstruction methods based on deep learning.

关键词： Deep learning models Three-dimensional reconstruction Recurrent neural network Deep autoencoder Generative adversarial network Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Containerization in Multi-Cloud Environment: Roles, Strategies, Challenges, and Solutions for Effective Implementation

arXiv

引用

arXiv 2024年

作者： Waseem, Muhammad Ahmad, Aakash Liang, Peng Akbar, Muhammad Azeem Khan, Arif Ali Ahmad, Iftikhar Setälä, Manu Mikkonen, Tommi Faculty of Information Technology and Communication Sciences Tampere University Tampere Finland School of Computing and Communications Lancaster University Leipzig Leipzig Germany School of Computer Science Wuhan University Wuhan China Software Engineering Department Lappeenranta-Lahti University of Technology Lappeenranta Finland M3S Empirical Software Engineering Research Unit University of Oulu Oulu Finland TietoEVRY Oy Tampere Finland Solita Oy Tampere Finland Faculty of Information Technology University of Jyväskylä Jyväskylä Finland

Containerization in a multi-cloud environment facilitates workload portability and optimized resource utilization. Containerization in multi-cloud environments has received significant attention in recent years both from academic research and industrial development perspectives. However, there exists no effort to systematically investigate the state of research on this topic. The aim of this research is to systematically identify and categorize the multiple aspects of containerization in multi-cloud environment. We conducted the Systematic Mapping Study (SMS) on the literature published between January 2013 and July 2024. One hundred twenty one studies were selected and the key results are: (1) Four leading themes on containerization in multi-cloud environment are identified: ‘Scalability and High Availability’, ‘Performance and Optimization’, ‘Security and Privacy’, and ‘Multi-Cloud Container Monitoring and Adaptation’. (2) Ninety-eight patterns and strategies for containerization in multi-cloud environment were classified across 10 subcategories and 4 categories. (3) Ten quality attributes considered were identified with 47 associated tactics. (4) Four catalogs consisting of challenges and solutions related to security, automation, deployment, and monitoring were introduced. The results of this SMS will assist researchers and practitioners in pursuing further studies on containerization in multi-cloud environment and developing specialized solutions for containerization applications in multi-cloud environment. © 2024, CC BY.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Research on Privacy Awareness Task Offloading Method Based on Privacy Entropy

SSRN

引用

SSRN 2023年

作者： Zhang, De-Gan An, Hong-Zhan Su, Hao Zhang, Ting Dong, Wen-Miao Zhang, Jie Jiang, Xing-Ru Tianjin University of Technology China The School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China The School of Electronic and Information Engineering Beijing Jiaotong University Beijing100044 China The School of Sports Economics and Management Tianjin University of Sport Tianjin301617 China The College of Software Beihang University Beijing100083 China

Mobile edge computing provides the possibility for efficient use of mobile devices, but the disclosure of user privacy is still a huge hidden danger. To solve the problem of locking users through device usage patterns, we propose a privacy aware computing offloading method based on privacy entropy. By quantifying privacy as privacy entropy, the problem is modeled as maximizing privacy entropy and minimizing computing offloading resource consumption. The Gaussian-Cauchy operator is proposed to improve the Harris Eagle algorithm, expand the search scope of the algorithm and enhance the ability to jump out of the local optimal. Experimental results show that this method can not only ensure the confusion of user information, but also minimize resource consumption and effectively solve the problem of privacy disclosure of behavior mode. © 2023, The Authors. All rights reserved.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Deep Global Distance Estimation Hashing for Image Retrieval

引用

IEEE Transactions on Big Data 2025年

作者： Xu, Mengfei Luo, Bowen Xu, Jianfeng Ding, Feng The School of Software Nanchang University Jiangxi330047 China Department of Computer Science University of Regina ReginaSKS4S 0A2 Canada Nanchang Key Laboratory for Innovative Application of Information Technology China

Hashing technology has an excellent high dimensional visual information encoding ability. It can map distance information from high dimensional to low dimensional Hamming space, which is widely used in large-scale image nearest neighbor search tasks. Most recent studies, such as pair-wise and triplet-wise, use local positional relations to construct hashing functions. These learning methods, which are only based on local information, will lead to an incoherent feature representation, especially for semantic similarity features. Therefore, we propose a global distance estimation hashing (DEH). The DEH establishes a deep hashing model by constructing global distance relations that can define a distance between every paired category. Thus the distance relations constructed by DEH include much more detailed information. In other words, DEH focuses on global distance relations and makes the division of boundaries have excellent performance, especially for those samples with subtle changes. After the mapping, the model quantization approach effectively decreases the quantization loss caused by transitioning from the real-valued space to the Hamming space. Numerous experiments show that our DEH achieves excellent results on CIFAR-10, NUS-WIDE and ImageNet. These achievements not only validate the effectiveness of DEH in general image hashing retrieval tasks but also demonstrate its significant advantages in handling the large-scale multimedia retrieval systems. © 2015 IEEE. All rights reserved.

关键词： Content based retrieval

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：