检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Hao, Bowen Zhang, Jing Li, Cuiping Chen, Hong Yin, Hongzhi Key Laboratory of Data Engineering Knowledge Engineering of Ministry of Education School of Information Renmin University of China China School of Information Technology and Electrical Engineering The University of Queensland Australia

The proliferation of massive open online courses (MOOCs) demands an effective way of course recommendation for jobs posted in recruitment websites, especially for the people who take MOOCs to find new jobs. Despite the advances of supervised ranking models, the lack of enough supervised signals prevents us from directly learning a supervised ranking model. This paper proposes a general automated weak supervision framework (AutoWeakS) via reinforcement learning to solve the problem. On the one hand, the framework enables training multiple supervised ranking models upon the pseudo labels produced by multiple unsupervised ranking models. On the other hand, the framework enables automatically searching the optimal combination of these supervised and unsupervised models. Systematically, we evaluate the proposed model on several datasets of jobs from different recruitment websites and courses from a MOOCs platform. Experiments show that our model significantly outperforms the classical unsupervised, supervised and weak supervision baselines. Copyright © 2020, The Authors. All rights reserved.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Abnormality Detection in Chest X-Ray Images Using Uncertainty Prediction Autoencoders 23rd

Abnormality Detection in Chest X-Ray Images Using Uncertaint...

引用

23rd International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2020

作者： Mao, Yifan Xue, Fei-Fei Wang, Ruixuan Zhang, Jianguo Zheng, Wei-Shi Liu, Hongmei School of Data and Computer Science Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing MOE Guangzhou China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Pazhou Lab Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China

ISBN: (纸本)9783030597245

Chest radiography is widely used in annual medical screening to check whether lungs are healthy or not. Therefore it would be desirable to develop an intelligent system to help clinicians automatically detect potential abnormalities in chest X-ray images. Here with only healthy X-ray images, we propose a new abnormality detection approach based on an autoencoder which outputs not only the reconstructed normal version of the input image but also a pixel-wise uncertainty prediction. Higher uncertainty often appears at normal region boundaries with relatively larger reconstruction errors, but not at potential abnormal regions in the lung area. Therefore the normalized reconstruction error by the uncertainty provides a natural measurement for abnormality detection in images. Experiments on two chest X-ray datasets show the state-of-the-art performance by the proposed approach. © 2020, Springer Nature Switzerland AG.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Relation extraction with proactive domain adaptation strategy 11

Relation extraction with proactive domain adaptation strateg...

引用

11th IEEE International Conference on knowledge Graph, ICKG 2020

作者： Zhong, Lingfeng Zhu, Yi Key Laboratory of Knowledge Engineering with Big Data (Heifei Unversity of Technology) Ministry of Education Heifei China School of Computer Science and Information Engineering Heifei University of Technology Heifei China Yangzhou University School of Computer Science and Technology Yangzhou China

ISBN: (数字)9781728181561

ISBN: (纸本)9781728181578

Relation extraction is an important information extraction task in many Natural Language Processing (NLP) applications, such as automatic knowledge graph construction, question answering, sentiment analysis, etc. However, relation extraction suffers from inappropriate associations between entities when the background knowledge of corpus is insufficiency. Despite the preprocessed external word vector bases can ease this problem, how to find a single word vector base as domain knowledge that contains all the required knowledge features is a huge challenge, and relation extraction with background knowledge is still open to further optimization. To address this problem, in this paper, we propose Relation Extraction method with Proactive Domain Adaptation Strategy (REPDAS for short) to introduce more knowledge features from different knowledge bases. More specifically, firstly, a convolutional network with a parameter-sharing layer is introduced for relation extraction, and word seeds that are important to relational feature exploitation are proactively picked by an attention mechanism during training. Secondly, the proactively-chosen word seeds and the previous parameter-sharing layer are utilized to establish a map between different domains. Our proposed method selectively avails both background knowledge and contextual features for relation extraction by incorporating the convolutional neural network with the proactively domain adaptation strategy. Experiments show that our method effectively enhances the performance of relation extraction compared with other baselines. © 2020 IEEE.

关键词： Domain Adaptation knowledge Graph Relation Extraction

来源：评论

学校读者我要写书评

暂无评论

Deep knn for medical image classification 23rd

Deep knn for medical image classification

引用

23rd International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2020

作者： Zhuang, Jiaxin Cai, Jiabin Wang, Ruixuan Zhang, Jianguo Zheng, Wei-Shi School of Data and Computer Science Sun Yat-sen University Guangzhou China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Key Laboratory of Machine Intelligence and Advanced Computing MOE Guangzhou China Pazhou Lab Guangzhou China

ISBN: (纸本)9783030597092

Human-level diagnostic performance from intelligent systems often depends on large set of training data. However, the amount of available data for model training may be limited for part of diseases, which would cause the widely adopted deep learning models not generalizing well. One alternative simple approach to small class prediction is the traditional k-nearest neighbor (kNN). However, due to the non-parametric characteristics of kNN, it is difficult to combine the kNN classification into the learning of feature extractor. This paper proposes an end-to-end learning strategy to unify the kNN classification and the feature extraction procedure. The basic idea is to enforce that each training sample and its K nearest neighbors belong to the same class during learning the feature extractor. Experiments on multiple small-class and class-imbalanced medical image datasets showed that the proposed deep kNN outperforms both kNN and other strong classifiers. © Springer Nature Switzerland AG 2020.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Towards Long-Range ENSO Prediction with an Explainable Deep Learning Model

arXiv

引用

arXiv 2025年

作者： Chen, Qi Cui, Yinghao Hong, Guobin Ashok, Karumuri Pu, Yuchun Zheng, Xiaogu Zhang, Xuanze Zhong, Wei Zhan, Peng Wang, Zhonglei Department of Ocean Science and Engineering Southern University of Science and Technology Shenzhen518055 China Department of Statistics and Data Science School of Economic Xiamen University Xiamen361005 China MOE Key Laboratory of Econometrics Xiamen University Xiamen361005 China Centre for Earth Ocean and Atmospheric Sciences University of Hyderabad Hyderabad India Baidu Inc. Beijing100085 China Shanghai Zhangjiang Institute of Mathematics Shanghai201203 China International Global Change Institute Hamilton New Zealand Key Laboratory of Water Cycle and Related Land Surface Processes Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing100101 China Wang Yanan Institute for Studies in Economics Xiamen University Xiamen361005 China

El Niño-Southern Oscillation (ENSO) is a prominent mode of interannual climate variability with far-reaching global impacts. Its evolution is governed by intricate air-sea interactions, posing significant challenges for long-term prediction. In this study, we introduce CTEFNet, a multivariate deep learning model that synergizes convolutional neural networks and transformers to enhance ENSO forecasting. By integrating multiple oceanic and atmospheric predictors, CTEFNet extends the effective forecast lead time to 20 months while mitigating the impact of the spring predictability barrier, outperforming both dynamical models and state-of-the-art deep learning approaches. Furthermore, CTEFNet offers physically meaningful and statistically significant insights through gradient-based sensitivity analysis, revealing the key precursor signals that govern ENSO dynamics, which align with well-established theories and reveal new insights about inter-basin interactions among the Pacific, Atlantic, and Indian Oceans. The CTEFNet’s superior predictive skill and interpretable sensitivity assessments underscore its potential for advancing climate prediction. Our findings highlight the importance of multivariate coupling in ENSO evolution and demonstrate the promise of deep learning in capturing complex climate dynamics with enhanced interpretability. © 2025, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Creating Something From Nothing: Unsupervised knowledge Distillation for Cross-Modal Hashing

Creating Something From Nothing: Unsupervised Knowledge Dist...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Hengtong Hu Lingxi Xie Richang Hong Qi Tian School of Computer Science and Information Engineering Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Huawei Inc.

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

In recent years, cross-modal hashing (CMH) has attracted increasing attentions, mainly because its potential ability of mapping contents from different modalities, especially in vision and language, into the same space, so that it becomes efficient in cross-modal data retrieval. There are two main frameworks for CMH, differing from each other in whether semantic supervision is required. Compared to the unsupervised methods, the supervised methods often enjoy more accurate results, but require much heavier labors in data annotation. In this paper, we propose a novel approach that enables guiding a supervised method using outputs produced by an unsupervised method. Specifically, we make use of teacher-student optimization for propagating knowledge. Experiments are performed on two popular CMH benchmarks, i.e., the MIRFlickr and NUS-WIDE datasets. Our approach outperforms all existing unsupervised methods by a large margin.

关键词： Training Semantics Computational modeling Feature extraction Dogs Training data Task analysis

来源：评论

学校读者我要写书评

暂无评论

Access control of blockchain based on dual-policy attribute-based encryption

Access control of blockchain based on dual-policy attribute-...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Daojun Han Jinyu Chen Lei Zhang Yatian Shen Xueheng Wang Yihua Gao Institute of Data and Knowledge Engineering School of Computer and Information Engineering Henan University Kaifeng China Henan Key Laboratory of Big Data Analysis and Processing School of Computer and Information Engineering Henan University Kaifeng China

In scenarios where multiple parties such as the Internet of Things and Supply Chains participate in data sharing and computing, when accessing data, users not only need to accept the forward access control of the data owner, but also needs to perform reverse access control on the data, so as to realize two-way access control. In the traditional blockchain, all users can participate in accounting and view transaction data, and only protect user privacy through “pseudo-anonymity”. The access rights of different users cannot be distinguished, which cannot meet the user's two-way access control needs. However, most of the existing blockchain-based access control schemes are one-way access control, which cannot meet the needs of users for two-way access control in scenarios such as the Internet of Things and Supply Chains. Therefore, it is particularly important to design a two-way access control mechanism suitable for application in the blockchain. On this basis, this paper proposes a dual strategy attribute-based encryption (ABE) scheme for distributed outsourcing. This scheme combines two existing schemes, ciphertext-policy ABE and key-policy ABE, and proposes two access structures and a structure of attribute sets. The primary access structure and the secondary attributes are stored in the ciphertext, and the secondary access structure and the primary attributes are stored in the user's private key. Only when the primary attribute set satisfies the primary access structure and the secondary attribute set satisfies the secondary access structure can the user unlock the ciphertext. This scheme has no single authorization center; instead, blockchain nodes jointly participate in authorization. In addition, the proposed scheme outsources the encryption and decryption of the ciphertext to blockchain nodes to reduce the computing pressure on users and can adapt to the decentralized environment of the blockchain and provide users with two-way access control services. Finally

关键词： Authorization data privacy High performance computing Conferences Supply chains Blockchain Permission

来源：评论

学校读者我要写书评

暂无评论

Creating something from nothing: Unsupervised knowledge distillation for cross-modal hashing

arXiv

引用

arXiv 2020年

作者： Hu, Hengtong Xie, Lingxi Hong, Richang Tian, Qi School of Computer Science and Information Engineering Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Huawei Inc.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Multi-fuzzy-objective graph pattern matching with big graph data

引用

Journal of database Management 2019年第4期30卷 24-40页

作者： Li, Lei Zhang, Fang Liu, Guanfeng Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei China Zhongxing Telecommunication Equipment Corporation Nanjing China Macquarie University Sydney Australia

Big graph data is different from traditional data and they usually contain complex relationships and multiple attributes. With the help of graph pattern matching, a pattern graph can be designed, satisfying special personal requirements and locate the subgraphs which match the required pattern. Then, how to locate a graph pattern with better attribute values in the big graph effectively and efficiently becomes a key problem to analyze and deal with big graph data, especially for a specific domain. This article introduces fuzziness into graph pattern matching. Then, a genetic algorithm, specifically an NSGA-II algorithm, and a particle swarm optimization algorithm are adopted for multifuzzy-objective optimization. Experimental results show that the proposed approaches outperform the existing approaches effectively. © 2019,IGI Global.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

LadRa-Net: Locally-aware dynamic re-read attention net for sentence semantic matching

arXiv

引用

arXiv 2021年

作者： Zhang, Kun Lv, Guangyi Wu, Le Chen, Enhong Liu, Qi Wang, Meng Key Laboratory of Knowledge Engineering with Big Data School of Computer and Information Hefei University of Technology Anhui Hefei230029 China AI Lab at Lenovo Research Beijing100094 China University of Science and Technology of China Hefei230026 China

Sentence semantic matching requires an agent to determine the semantic relation between two sentences, which is widely used in various natural language tasks, such as Natural Language Inference (NLI), Paraphrase Identification (PI), and so on. Much recent progress has been made in this area, especially attention-based methods and pre-trained language model based methods. However, most of these methods focus on all the important parts in sentences in a static way and only emphasize how important the words are to the query, inhibiting the ability of attention mechanism. In order to overcome this problem and boost the performance of attention mechanism, we propose a novel dynamic re-read attention, which can pay close attention to one small region of sentences at each step and re-read the important parts for better sentence representations. Based on this attention variation, we develop a novel Dynamic Re-read Network (DRr-Net) for sentence semantic matching. Moreover, selecting one small region in dynamic re-read attention seems insufficient for sentence semantics, and employing pre-trained language models as input encoders will introduce incomplete and fragile representation problems. To this end, we extend DRr-Net to Locally-Aware Dynamic Re-read Attention Net (LadRa-Net), in which local structure of sentences is employed to alleviate the shortcoming of Byte-Pair Encoding (BPE) in pre-trained language models and boost the performance of dynamic reread attention. Extensive experiments on two popular sentence semantic matching tasks demonstrate that DRr-Net can significantly improve the performance of sentence semantic matching. Meanwhile, LadRa-Net is able to achieve better performance by considering the local structures of sentences. In addition, it is exceedingly interesting that some discoveries in our experiments are consistent with some findings of psychological research. © 2021, CC BY.

关键词： Computational linguistics

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：