检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Long, Xianzhong Peng, Chen Li, Yun School of Computer Science Nanjing University of Posts and Telecommunications Nanjing210023 China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing210023 China

In contrastive self-supervised learning, positive samples are typically drawn from the same image but in different augmented views, resulting in a relatively limited source of positive samples. An effective way to alleviate this problem is to incorporate the relationship between samples, which involves including the top-K nearest neighbors of positive samples. However, the problem of false neighbors (i.e., neighbors that do not belong to the same category as the positive sample) is an objective but often overlooked challenge due to the query of neighbor samples without supervision information. In this paper, we present a simple self-supervised learning framework called Mixed Nearest-Neighbors for Self-Supervised Learning (MNN). MNN optimizes the influence of neighbor samples on the semantics of positive samples through an intuitive weighting approach and image mixture operations. The results demonstrate that MNN exhibits exceptional generalization performance and training efficiency on four benchmark datasets. © 2023, CC BY.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Dafl: Domain Adaptation-Based Federated Learning for Privacy-Preserving Biometric Recognition

SSRN

引用

SSRN 2023年

作者： Wang, Zhousheng Yang, Geng Dai, Hua Bai, Yunlu School of Computer Science Nanjing University of Posts and Telecommunications Nanjing210023 China Jiangsu Key Laboratory of Big data Security & Intelligent Processing Nanjing210023 China

With the introduction of data protection regulation in various countries, traditional centralized learning for the exploitation of sensitive biological information will gradually become unsustainable. We take face and speaker recognition systems as examples, to consider the possibility of implementing them using federated learning. It is known that federated learning methods still have some issues to be solved, e.g., parameter updates delivered can still reveal user privacy. Besides, existing privacy-preserving methods such as encryption and perturbation could pose other problems, including low accuracy and high training overhead, which can be more prominent in biometric recognition scenarios. We adopt the idea of domain adaptation and propose a new federated learning framework, DAFL, focusing on the improvement of the training efficiency and model performance, to achieve a practical privacy-preserving biometric recognition scheme for the first time. We also design a special dropout method for it to address the possible imbalance of biometric samples across users. Experiments on real-world datasets show that our approach can achieve up to 95.6% and 97.9% accuracy in face recognition and speaker recognition tasks, respectively, under medium privacy settings. Compared with existing work, it can save 56.0% of training time with a 3.1% accuracy loss in the best case. © 2023, The Authors. All rights reserved.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

On Link Formation in Heterogeneous Information Networks: A View Based on Multi-Label Learning

On Link Formation in Heterogeneous Information Networks: A V...

引用

International Conference on Advances in Social Network Analysis and Mining, ASONAM

作者： Ke-Jia Chen Shijun Xue Yun Li Bin Liu Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing Jiangsu China College of Computer Science Nanjing University of Posts and Telecommunications Nanjing Jiangsu China

ISBN: (数字)9781450349932

ISBN: (纸本)9781450349932

This paper studies the problem of relationship prediction in heterogeneous information networks. Our goal is not only to predict links/relationships more accurately but also to provide more viable paths to facilitate the formation of new links/relationships. A relationship prediction method based on multi-label learning named ML 3 P is proposed. In ML 3 P, each meta-path between nodes is regarded as a type of relationship and is given a label. Under the framework of multi-label learning, any potential relationship including the target relationship can be predicted. The results of comparative experiments in DBLP and Twitter datasets show that ML 3 P better uses heterogeneous information in supervised learning process and thus achieves better performance. Moreover, our method can output the correlation between relationships.

关键词： Twitter Task analysis Feature extraction Training Measurement Correlation

来源：评论

学校读者我要写书评

暂无评论

Recommendation system based on trusted relation transmission

Recommendation system based on trusted relation transmission

引用

International Conference on intelligent System and Knowledge Engineering, ISKE

作者： Yixiong Bian Huakang Li Jiangsu Key Lab of Big Data and Security and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi China

With the rapid development of the internet, applications of recommendation systems for online shops and entertainment platforms become more and more popular. In order to improve the effectiveness of recommendation, external information has been incorporated into various algorithms, such as location and social relationship. However, most algorithms only focus on the introduction of external information without depth analysis of the intrinsic mechanism in the external information. This paper proposed a transfer model of social trusted relationship, and optimized the reliability of the transfer model using pruning algorithm based on original trust recommendation. A credible social relationship macro-transfer model based on iterations of new credible relationships is defined by the similarity of social relationships. With a certain interest topic as a source of information, a micro-transfer model achieves the theme of interest and credibility of the expansion using social information dissemination algorithm. To demonstrate the effectiveness of the macro and micro credible transfer models, we used the Mantra search tree pruning algorithm and the optimization algorithm of similar category replacing similar products. The experimental results show that the proposed method based on the macroscopic and microscopic transfer models of the trusted relationship enhances the success rate and stability of the recommended system.

关键词： Collaboration Reliability Social network services Heuristic algorithms Optimization System performance Convergence

来源：评论

学校读者我要写书评

暂无评论

SLBERT: An Improved FLAT-BERT for Named Entity Recognition

SSRN

引用

SSRN 2022年

作者： Fei, Yuefan Xu, Xiaolong Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Jiangsu Nanjing China School of Computer Science Nanjing University of Posts and Telecommunications Jiangsu Nanjing China

Named Entity Recognition (NER) aims to identify named entities mentioned in unstructured text and classify them into predefined named entity classes. Although models using word fusion have achieved relatively high performance, the recognition of ambiguous entities in text remains challenging, and the performance of the models depends on a sufficient amount of manually labeled data;exploring models that fuse more feature dimensions and schemes that fuse existing datasets is of farreaching interest. In this work, we propose an improved scheme of FLAT-BERT, SLBERT, that can be used in the field of named entity *** scheme consists of two phases that more fully exploit the global semantics of the text. In the first stage, the model is trained based on the current dataset, another dataset is predicted for cross-dataset fusion, and the correctness of label annotation is improved by entity confidence modeling. In the second stage, the global semantics of the text is extracted using Sentence BERT and embedded into the feature matrix encoded using Lattice BERT for subsequent Token classification. We have conducted experiments on several datasets, and the experimental results demonstrate the effectiveness of the proposed scheme in this paper. In terms of F1 values, compared with FLAT-BERT, the improvement is 0.15%, 0.34%, 0.61%, and 0.58% on datasets OntoNotes, MSRA, Resume, and Weibo, respectively. © 2022, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

ILAPF: INCREMENTAL LEARNING ASSISTED PARTICLE FILTERING

arXiv

引用

arXiv 2017年

作者： Liu, Bin School of Computer Science Jiangsu Key Lab of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing210023 China

This paper is concerned with dynamic system state estimation based on a series of noisy measurement with the presence of outliers. An incremental learning assisted particle filtering (ILAPF) method is presented, which can learn the value range of outliers incrementally during the process of particle filtering. The learned range of outliers is then used to improve subsequent filtering of the future state. Convergence of the outlier range estimation procedure is indicated by extensive empirical simulations using a set of differing outlier distribution models. The validity of the ILAPF algorithm is evaluated by illustrative simulations, and the result shows that ILAPF is more accurate and faster than a recently published state-of-the-art robust particle filter. It also shows that the incremental learning property of the ILAPF algorithm provides an efficient way to implement transfer learning among related state filtering tasks. Copyright © 2017, The Authors. All rights reserved.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Using deep learning to recognize biomedical entities

Using deep learning to recognize biomedical entities

引用

International Conference on intelligent System and Knowledge Engineering, ISKE

作者： Xuemin Yang Zhifei Zhang Ronggen Yang Daoyu Huang Geng Yang Lejun Gong Jiangsu Key Laboratory of Big Data Security &Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China Faculty Intelligent Science and Control Engineering Jinling Institute of Technology Nanjing China

With the rapid growth of the high-throughput biological technology, it brings biomedical big omics' data containing literature and annotated data. Especially, a wealth of relevant information exists in various types of biomedical literature. Text mining has emerged as a potential solution to achieve knowledge for bridging between the free text and structured representation of biomedical information. In this work, we used deep learning to recognize biomedical entities. We obtained 84.0% precision, 69.5% recall, and 76.1% F-score aiming at the GENIA corpus, and obtained 91.3% precision, 91.1% recall, and 91.2% F-score aiming at the BioCreAtIvE II Gene Mention corpus. Experimental results show that our proposed approach is promising for developing biomedical text mining technology in biomedical entity recognition.

关键词： Machine learning Neural networks Text mining Dictionaries Distributed databases Biological system modeling Telecommunications

来源：评论

学校读者我要写书评

暂无评论

ILAPF: INCREMENTAL LEARNING ASSISTED PARTICLE FILTERING

ILAPF: INCREMENTAL LEARNING ASSISTED PARTICLE FILTERING

引用

IEEE International Conference on Acoustics, Speech and Signal processing

作者： Bin Liu School of Computer Science Jiangsu Key Lab of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing 210023 China

ISBN: (纸本)9781538646595

关键词： incremental learning outlier particle filtering robust state filtering transfer learning outliers Transfer (Psychology) Particle filters learning (artificial intelligence) Filtration State estimation

来源：评论

学校读者我要写书评

暂无评论

data-DRIVEN MODEL SET DESIGN FOR MODEL AVERAGED PARTICLE FILTER

arXiv

引用

arXiv 2019年

作者： Liu, Bin School of Computer Science Jiangsu Key Lab of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing210023 China

This paper is concerned with sequential state filtering in the presence of nonlinearity, non-Gaussianity and model uncertainty. For this problem, the Bayesian model averaged particle filter (BMAPF) is perhaps one of the most efficient solutions. Major advances of BMAPF have been made, while it still lacks a generic and practical approach to design the model set. This paper fills in this gap by proposing a generic data-driven method for BMAPF model set design. Unlike existent methods, the proposed solution does not require any prior knowledge on the parameter value of the true model;it only assumes that a small number of noisy observations are pre-obtained. The Bayesian optimization (BO) method is adapted to search the model components, each of which is associated with a specific segment of the pre-obtained data set. The average performance of these model components is guaranteed since each one’s parameter value is elaborately tuned via BO to maximize the marginal likelihood. The diversity in the model components is also ensured, as different components match the different segments of the pre-obtained data set, respectively. Computer simulations are used to demonstrate the effectiveness of the proposed method. Copyright © 2019, The Authors. All rights reserved.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

UB-CQA: A user attribute based community question answering system

UB-CQA: A user attribute based community question answering ...

引用

International Conference on intelligent System and Knowledge Engineering, ISKE

作者： Ziye Zhu Xiaoqian Liu Huakang Li Tao Li School of Computer Science Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing Jiangsu China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

intelligent Community Question Answering (CQA) system is a popular research topic in Natural Language processing (NLP) area. Recently, the development of distributed data mining has significantly improved the efficiency of the searching and sorting operations in CQA database. However, problems are left unanswered such as how to choose the best answer among multiple candidates for a single question. To solve this issue, we design a CQA system called UB-CQA. First, in database refinement part, we construct an optimized and structured database by the best answer choosing method leveraging user attribute provided by the response provider. Second, in human-computer part, the UB-CQA is able to search and provide a more satisfying answer to users by similarity calculation and re-ranking method leveraging text categorization information. Empirical evaluations show that the best answer choosing and the candidate question re-ranking methods bring great improvements in accuracy and reliability.

关键词： databases Knowledge based systems Mathematical model Knowledge discovery Internet Computer science

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：