检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Liu, Linsong Chen, Ke-Jia Liu, Zheng Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Jiangsu Nanjing210023 China School of Computer Science Nanjing University of Posts and Telecommunications Jiangsu Nanjing210023 China State Key Laboratory of Novel Software Technology Nanjing University Jiangsu Nanjing210093 China

Directed graph is able to model asymmetric relationships between nodes and research on directed graph embedding is of great significance in downstream graph analysis and inference. Learning source and target embeddings of nodes separately to preserve edge asymmetry has become the dominant approach, but also poses challenge for learning representations of low or even zero in/out degree nodes that are ubiquitous in sparse graphs. In this paper, a collaborative bi-directional aggregation method (COBA) for directed graph embedding is proposed. Firstly, the source and target embeddings of the central node are learned by aggregating from the counterparts of the source and target neighbors, respectively;Secondly, the source/target embeddings of the zero in/out degree central nodes are enhanced by aggregating the counterparts of opposite-directional neighbors (i.e. target/source neighbors);Finally, source and target embeddings of the same node are correlated to achieve collaborative aggregation. Both the feasibility and rationality of the model are theoretically analyzed. Extensive experiments on real-world datasets demonstrate that COBA comprehensively outperforms state-of-the-art methods on multiple tasks and meanwhile validates the effectiveness of proposed aggregation strategies. © 2023, The Authors. All rights reserved.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

Analysis on Attention Mechanism Application Schemes for Automatic Question Answering Systems

Analysis on Attention Mechanism Application Schemes for Auto...

引用

IEEE International Conference on Progress in Informatics and Computing (PIC)

作者： Xinyuan Lu Xiaolong Xu Yanfei Sun Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing Jiangsu China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing Jiangsu China Office of Scientific R&D Nanjing University of Posts and Telecommunications Nanjing Jiangsu China

ISBN: (纸本)9781538676738;9781538676721

An automatic question answering system is generally composed of the question analysis module, the information retrieval module, the answer selection module, etc. The core component of automatic question answering system is the answer selection module, which focuses on extracting adequate information from the questions and answers and representing them effectively. The performance of answer selection directly determines the quality of the answers submitted to users. In this paper, we studied the answer selection schemes, especially the Attentive LSTM scheme, focusing on the application of the attention mechanism commonly utilized in deep learning models. Meanwhile, a self-attentive LSTM is proposed by combining the Attentive LSTM with self-attention which is capable of extracting the local features and the global features of texts at the same time. In addition, a multi-attentive LSTM is proposed so that multiple parts of information in the question are available for the answer. We performed a series of experiments based on the datasets InsuranceQA and TrecQA, compared and analyzed on the performances of the above schemes.

关键词： Feature extraction Task analysis Neural networks Logic gates data mining Knowledge discovery Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Point Cloud Registration Method for Substations Based on an Improved SAC-IA Algorithm

A Point Cloud Registration Method for Substations Based on a...

引用

Chinese Automation Congress (CAC)

作者： Lei Wang Yiping Chen Haonan Zong Lulu Wang Jun Yin School of Computer Nanjing University of Posts and Telecommunications Nanjing PR China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing PR China School of Internet of Things Nanjing University of Posts and Telecommunications Nanjing PR China

This paper proposes a point cloud registration method for substations based on an improved SAC-IA algorithm. This method optimizes the SAC-IA algorithm by filtering the randomly selected point pairs to ensure that the triangles formed by the selected points in the model and scene point clouds have certain similarities. Furthermore, the registration error judgment of the SAC-IA algorithm has been improved. In addition to using the Euclidean distance between the registered model and scene point clouds as the judgment standard, this method also considers the SHOT difference and average curvature difference. Successful registration is only considered when all three standards are satisfied. The experimental research shows that the time performance of this method is twice as high as that of the traditional SAC-IA algorithm on average, and the recognition accuracy is improved in the recognition results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Online Attentive Kernel-Based Temporal Difference Learning

arXiv

引用

arXiv 2022年

作者： Yang, Guang Chen, Xingguo Yang, Shangdong Wang, Huihui Dong, Shaokang Gao, Yang The the Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications National Engineering Laboratory for Agri-Product Quality Traceability Beijing Technology and Business University China The State Key Laboratory for Novel Software Technology Nanjing University China The PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China

With rising uncertainty in the real world, online Reinforcement Learning (RL) has been receiving increasing attention due to its fast learning capability and improving data efficiency. However, online RL often suffers from complex Value Function Approximation (VFA) and catastrophic interference, creating difficulty for the deep neural network to be applied to an online RL algorithm in a fully online setting. Therefore, a simpler and more adaptive approach is introduced to evaluate value function with the kernel-based model. Sparse representations are superior at handling interference, indicating that competitive sparse representations should be learnable, non-prior, non-truncated and explicit when compared with current sparse representation methods. Moreover, in learning sparse representations, attention mechanisms are utilized to represent the degree of sparsification, and a smooth attentive function is introduced into the kernel-based VFA. In this paper, we propose an Online Attentive Kernel-Based Temporal Difference (OAKTD) algorithm using two-timescale optimization and provide convergence analysis of our proposed algorithm. Experimental evaluations showed that OAKTD outperformed several Online Kernel-based Temporal Difference (OKTD) learning algorithms in addition to the Temporal Difference (TD) learning algorithm with Tile Coding on public Mountain Car, Acrobot, CartPole and Puddle World tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Identifying outliers in astronomical images with unsupervised machine learning

arXiv

引用

arXiv 2022年

作者： Han, Yang Zou, Zhiqiang Li, Nan Chen, Yanli School of Computer Science Nanjing University of Posts and Telecommunications Jiangsu Nanjing China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Jiangsu Nanjing China Key Laboratory of Optical Astronomy National Astronomical Observatories Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Astronomical outliers, such as unusual, rare or unknown types of astronomical objects or phenomena, constantly lead to the discovery of genuinely unforeseen knowledge in astronomy. More unpredictable outliers will be uncovered in principle with the increment of the coverage and quality of upcoming survey data. However, it is a severe challenge to mine rare and unexpected targets from enormous data with human inspection due to a significant workload. Supervised learning is also unsuitable for this purpose since designing proper training sets for unanticipated signals is unworkable. Motivated by these challenges, we adopt unsupervised machine learning approaches to identify outliers in the data of galaxy images to explore the paths for detecting astronomical outliers. For comparison, we construct three methods, which are built upon the k-nearest neighbors (KNN), Convolutional Auto-Encoder (CAE) + KNN, and CAE + KNN + Attention Mechanism (attCAE KNN) separately. Testing sets are created based on the Galaxy Zoo image data published online to evaluate the performance of the above methods. Results show that attCAE KNN achieves the best recall (78%), which is 53% higher than the classical KNN method and 22% higher than CAE+KNN. The efficiency of attCAE KNN (10 minutes) is also superior to KNN (4 hours) and equal to CAE+KNN (10 minutes) for accomplishing the same task. Thus, we believe it is feasible to detect astronomical outliers in the data of galaxy images in an unsupervised manner. Next, we will apply attCAE KNN to available survey datasets to assess its applicability and reliability. Copyright © 2022, The Authors. All rights reserved.

关键词： k-nearest neighbors

来源：评论

学校读者我要写书评

暂无评论

Improving the Efficiency of Blockchain Applications with Smart Contract based Cyber-insurance

Improving the Efficiency of Blockchain Applications with Sma...

引用

IEEE International Conference on Communications (ICC)

作者： Jia Xu Yongqi Wu Xiapu Luo Dejun Yang Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China Department of Computing The Hong Kong Polytechnic University Hongkong China Department of Computer Science Colorado School of Mines Golden USA

ISBN: (数字)9781728150895

ISBN: (纸本)9781728150901

Blockchain based applications benefit from decentralization, data privacy, and anonymity. However, they may suffer from inefficiency due to underlying blockchain. In this paper, we aim to address this limitation while still enjoying the privacy and anonymity. Taking the blockchain based crowdsourcing system as an example, we propose a new smart contract based cyber-insurance framework, which can greatly shorten the delay, and enable the workers to obtain the economic compensation for increased security risk caused by a conflict between the need to provide service quickly and delay in payment. We model the process of determining insurance premium and number of confirmations as a Stackelberg Game and prove the existence of Stackelberg Equilibria, at which the utility of the requester is maximized, and none of the workers can improve its utility by unilaterally deviating from its current strategy. The experimental results show that our framework can definitely improve the time efficiency of crowdsourcing. Particularly, it takes on average only 33% of the time required by the naive blockchain based crowdsouring solution for time-sensitive cases.

关键词： Contracts Crowdsourcing Task analysis Insurance Bitcoin

来源：评论

学校读者我要写书评

暂无评论

Classifying Galaxy Morphologies with Few-Shot Learning

arXiv

引用

arXiv 2022年

作者： Zhang, Zhirui Zou, Zhiqiang Li, Nan Chen, Yanli College of Computer Nanjing University of Posts and Telecommunications Nanjing China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Jiangsu Nanjing China Key Laboratory of Optical Astronomy National Astronomical Observatories Chinese Academy of Sciences Beijing China University of Chinese Academy of Science Beijing China

The taxonomy of galaxy morphology is critical in astrophysics as the morphological properties are powerful tracers of galaxy evolution. With the upcoming Large-scale Imaging Surveys, billions of galaxy images challenge astronomers to accomplish the classification task by applying traditional methods or human inspection. Consequently, machine learning, in particular supervised deep learning, has been widely employed to classify galaxy morphologies recently due to its exceptional automation, efficiency, and accuracy. However, supervised deep learning requires extensive training sets, which causes considerable workloads;also, the results are strongly dependent on the characteristics of training sets, which leads to biased outcomes potentially. In this study, we attempt Few-shot Learning to bypass the two issues. Our research adopts the dataset from Galaxy Zoo Challenge Project on Kaggle, and we divide it into five categories according to the corresponding truth table. By classifying the above dataset utilizing few-shot learning based on Siamese Networks and supervised deep learning based on AlexNet, VGG 16, and ResNet 50 trained with different volumes of training sets separately, we find that few-shot learning achieves the highest accuracy in most cases, and the most significant improvement is 21% compared to AlexNet when the training sets contain 1000 images. In addition, to guarantee the accuracy is no less than 90%, few-shot learning needs ∼6300 images for training, while ResNet 50 requires ∼13000 images. Considering the advantages stated above, foreseeably, few-shot learning is suitable for the taxonomy of galaxy morphology and even for identifying rare astrophysical objects, despite limited training sets consisting of observational data only. Copyright © 2022, The Authors. All rights reserved.

关键词： Galaxies

来源：评论

学校读者我要写书评

暂无评论

VideoGIS data retrieval based on multi-feature fusion

VideoGIS data retrieval based on multi-feature fusion

引用

International Conference on intelligent System and Knowledge Engineering, ISKE

作者： Haihong Dai Bin Hu Qian Cui Zhiqiang Zou College of Computer Nanjing University of Posts and Telecommunications Nanjing Jiangsu China College of Geographic Science Nanjing Normal University Nanjing China Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing Jiangsu China Key Laboratory of Virtual Geographic Environment (Nanjing Normal University) Ministry of Education Nanjing China

With the rapid development of smart cities and the advance of city safety and defense demands, the question that how to accurately discover and retrieve the data that users request from VideoGIS data faces a series of bottleneck problems. VideoGIS data retrieval is one of the important ways to solve above problems. In order to accelerate the rate of feature matching and improve the efficiency of the video retrieval, a new method of VideoGIS data retrieval based on multi-feature fusion is proposed in this paper. The method firstly use video frame difference based on Euclidean distance to extract the key frames under the spatial and temporal sampling of the video. On the basis of this, the global features (e.g. color, shape, texture) are fused by different weighted coefficients, then the feature vector, as the video multi-feature fusion representation, can be constructed by fusing the global features and local features. Based on the multi-feature fusion, correlation between video features is made full use. Compared with the method of single feature and two-feature fusion, the experimental results indicate that the proposed retrieval method has better retrieval effect.

关键词： Feature extraction Image color analysis data mining Correlation Euclidean distance Shape Streaming media

来源：评论

学校读者我要写书评

暂无评论

Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features 38

Not All Diffusion Model Activations Have Been Evaluated as D...

引用

38th Conference on Neural Information processing Systems, NeurIPS 2024

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is available at this url. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques 38

Suppress Content Shift: Better Diffusion Features via Off-th...

引用

38th Conference on Neural Information processing Systems, NeurIPS 2024

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Yang, Zhiyong Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Computer Science and Tech. University of Chinese Academy of Sciences China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is available at this url. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

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：