检索结果-内蒙古大学图书馆

MMCGAN: Generative Adversarial network with explicit manifold prior

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zheng, Guanhua Sang, Jitao Xu, Changsheng University of Science and Technology of China School of Computer and Information Technology Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing100044 China National Lab of Pattern Recognition Institute of Automation CAS University of Chinese Academy of Sciences Beijing100190 China

Generative Adversarial network(GAN) provides a good generative framework to produce realistic samples, but suffers from two recognized issues as mode collapse and unstable training. In this work, we propose to employ explicit manifold learning as prior to alleviate mode collapse and stabilize training of GAN. Since the basic assumption of conventional manifold learning fails in case of sparse and uneven data distribution, we introduce a new target, Minimum Manifold Coding (MMC), for manifold learning to encourage simple and unfolded manifold. In essence, MMC is the general case of the shortest Hamiltonian Path problem and pursues manifold with minimum Riemann volume. Using the standardized code from MMC as prior, GAN is guaranteed to recover a simple and unfolded manifold covering all the training data. Our experiments on both the toy data and real datasets show the effectiveness of MMCGAN in alleviating mode collapse, stabilizing training, and improving the quality of generated samples. Copyright © 2020, The Authors. All rights reserved.

关键词： Generative adversarial networks

Generalized association and deep understanding method for big video data processing

学校读者我要写书评

暂无评论

Generalized association and deep understanding method for bi...

2019 IEEE International Conferences on Ubiquitous computing and Communications and data science and Computational Intelligence and Smart computing, networking and Services, IUCC/DSCI/SmartCNS 2019

作者： Xu, Lin Wu, Wei Lv, Wanghan Wang, Dong Science and Technology in Information System Engineering Lab Nanjing Research Institute of Electronic Engineering Nanjing China School of Information Science and Engineering University of Jinan China Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan China

ISBN: (纸本)9781728152097

In Big data Era, it is becoming more and more important to timely and efficient processing of massive videos, and mining of the value information contained in them. This paper studies chaotic compressed sensing theory and uses Long-term and short-term memory networks (LSTM) algorithm to generate a summary of the content of video behavior track. It has already to apply the proposed method in target recognition and tracking, and the recognition rate achieves more than 86%. © 2019 IEEE.

关键词： Big data

Fair and autonomous sharing of federate learning models in mobile Internet of Things

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Hao, Xiaohan Ren, Wei Xiong, Ruoting Zheng, Xianghan Zhu, Tianqing Xiong, Neal N. School of Computer Science China University of Geoscience Wuhan China Guangxi Key Laboratory of Cryptography and Information Security Guilin541004 China Key Laboratory of Network Assessment Technology CAS Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China Mingbyte Technology QingDao China School of Software University of Technology Sydney UltimoNSW2007 Australia Dept. of Mathematics and Computer Science Northeastern State University United States

Federate learning can conduct machine learning as well as protect the privacy of self-owned training data on corresponding ends, instead of having to upload to a central trusted data aggregation server. In mobile scenarios, a centralized trusted server may not be existing, and even though it exists, the delay will not be manageable, e.g., smart driving cars. Thus, mobile federate learning at the edge with privacy-awareness is attracted more and more attentions. It then imposes a problem - after data are trained on a mobile terminal to obtain a learned model, how to share the model parameters among others to create more accurate and robust accumulative final model. This kind of model sharing confronts several challenges, e.g., the sharing must be conducted without a third trusted party (autonomously), and the sharing must be fair as model training (by training data)is valuable. To tackle the above challenges, we propose a smart contract and IPFS (Inter-Planetary File System) based model sharing protocol and algorithms to address the challenges. The proposed protocol does not rely on a trusted third party, where individual-learned models are shared/stored in corresponding ends. Conducted through extensive experiments, three main steps of the proposed protocol are evaluated. The average executive time of the three steps are 0.059s, 0.060s and 0.032s, demonstrating its efficiency. Copyright © 2020, The Authors. All rights reserved.

关键词： Smart contract

HAS-QA: Hierarchical answer spans model for open-domain question answering

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Pang, Liang Lan, Yanyan Guo, Jiafeng Xu, Jun Su, Lixin Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Department of Statistics University of California Berkeley

This paper is concerned with open-domain question answering (i.e., OpenQA). Recently, some works have viewed this problem as a reading comprehension (RC) task, and directly applied successful RC models to it. However, the performances of such models are not so good as that in the RC task. In our opinion, the perspective of RC ignores three characteristics in OpenQA task: 1) many paragraphs without the answer span are included in the data collection;2) multiple answer spans may exist within one given paragraph;3) the end position of an answer span is dependent with the start position. In this paper, we first propose a new probabilistic formulation of OpenQA, based on a three-level hierarchical structure, i.e., the question level, the paragraph level and the answer span level. Then a Hierarchical Answer Spans Model (HAS-QA) is designed to capture each probability. HAS-QA has the ability to tackle the above three problems, and experiments on public OpenQA datasets show that it significantly outperforms traditional RC baselines and recent OpenQA baselines. Copyright © 2019, The Authors. All rights reserved.

关键词：

Design of Target Behavior Intelligent Analysis System Based on Distributed computing

学校读者我要写书评

暂无评论

Design of Target Behavior Intelligent Analysis System Based ...

Signal, Information and data Processing (ICSIDP), IEEE International Conference on

作者： Xinlong Pan Xueqi Cheng Libo Yao Zhenqiu Zhu Biao Ding Tiantian Tang Minbo Li Chuanhui Liu CAS Key Laboratory of Network Data Science & Technology Inistitute of Computing Technology Beijing China Institute of Information Fusion Naval Aviation University Yantai China School of Software Fudan University Shanghai China

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

Through the fusion processing of target data obtained by radar, electronic reconnaissance, space reconnaissance, technical reconnaissance and civil cooperative system in early warning and surveillance system, multidimensional target data including explicit state information such as target attributes, type, position, speed and course could be obtained. The latent potential information, such as regular behavior, intention and threat degree, need to be mastered by human intelligence and experience analysis. It is urgent to use big data mining technology to realize intelligent analysis of target behavior. Based on the analysis of big data related technologies, this paper designs an intelligent target behavior analysis system based on distributed computing, which provides theoretical and technical support for intelligent upgrading of intelligence processing systems and command decision systems.

关键词：

Optimizing network resource allocation with graph pointer neural network in large-scale AI systems

学校读者我要写书评

暂无评论

Digital Communications and networks 2024年

作者： Peiying Zhang Yilin Li Athanasios V. Vasilakos Konstantin Igorevich Kostromitin Jianyong Zhang Mohsen Guizani Qingdao Institute of Software College of Computer Science and Technology China University of Petroleum (East China) Qingdao 266580 China State Key Laboratory of Integrated Services Networks Xidian University Xi'an 710071 China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan 250013 China Department of Networks and Communications College of Computer Science and Information Technology Imam Abdulrahman Bin Faisal University P.O. Box 1982 Dammam 31441 Saudi Arabia Department of Physics of Nanoscale Systems South Ural State University Chelyabinsk 454080 the Russian Federation Institute of Lightwave Technology Beijing Jiaotong University Beijing 100044 China Key Lab of All Optical Network and Advanced Telecommunication of EMC Institute of Lightwave Technology Beijing Jiaotong University Beijing 100044 China Machine Learning Department Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI) Abu Dhabi 999041 United Arab Emirates

For increasingly complex communication demands of large-scale AI communication systems, the Space-Air-Ground Integrated network (SAGIN) better caters to demands but also raises concerns about resource scarcity and diversity. This paper innovatively combines Graph Pointer Neural networks (GPNN) and Reinforcement Learning (RL) to enhance resource allocation efficiency. The method leverages the advantages of GPNN in handling graph data and RL in optimizing decisions in dynamic environments. It also targets the optimization goal of maximizing resource allocation while minimizing deployment latency. This paper begins by modeling SAGIN and elucidating the SAGIN logical architecture based on Software-defined networking (SDN). Subsequently, it introduces an SFC deployment algorithm aimed at joint optimization of resource allocation and latency. The algorithm leverages GPNN and RL to deploy virtual nodes and links, with the goal of optimizing resource allocation and deployment latency. Experiment findings conclusively demonstrate that the efficacy of proposed algorithm in effectively weighing limited heterogeneous resources and minimum mapping delay. Notably, when compared to three other SFC mapping algorithms MLRL, NFVdeep, and RL, the proposed algorithm consistently outperforms them, with an average improvement of 10.17% in long-term average reward/cost, 11.21% in link resource utilization ratio, 15.34% in node resource utilization ratio, and 16.38% in acceptance ratio.

关键词： Space-air-ground integrated network Topological structure Reinforcement learning Service function chain Graph pointer neural network

A Deep Look into Neural Ranking Models for Information Retrieval

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Guo, Jiafeng Fan, Yixing Pang, Liang Yang, Liu Ai, Qingyao Zamani, Hamed Wu, Chen Croft, W. Bruce Cheng, Xueqi University of Chinese Academy of Sciences Beijing China Cas Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China Center for Intelligent Information Retrieval University of Massachusetts Amherst AmherstMA United States

Ranking models lie at the heart of research on information retrieval (IR). During the past decades, different techniques have been proposed for constructing ranking models, from traditional heuristic methods, probabilistic methods, to modern machine learning methods. Recently, with the advance of deep learning technology, we have witnessed a growing body of work in applying shallow or deep neural networks to the ranking problem in IR, referred to as neural ranking models in this paper. The power of neural ranking models lies in the ability to learn from the raw text inputs for the ranking problem to avoid many limitations of hand-crafted features. Neural networks have sufficient capacity to model complicated tasks, which is needed to handle the complexity of relevance estimation in ranking. Since there have been a large variety of neural ranking models proposed, we believe it is the right time to summarize the current status, learn from existing methodologies, and gain some insights for future development. In contrast to existing reviews, in this survey, we will take a deep look into the neural ranking models from different dimensions to analyze their underlying assumptions, major design principles, and learning strategies. We compare these models through benchmark tasks to obtain a comprehensive empirical understanding of the existing techniques. We will also discuss what is missing in the current literature and what are the promising and desired future directions. Copyright © 2019, The Authors. All rights reserved.

关键词： Information retrieval

A quantum-inspired classical algorithm for separable non-negative matrix factorization

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Chen, Zhihuai Li, Yinan Sun, Xiaoming Yuan, Pei Zhang, Jialin CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Centrum Wiskunde & Informatica and QuSoft Science Park 123 Amsterdam1098XG Netherlands

Non-negative Matrix Factorization (NMF) asks to decompose a (entry-wise) non-negative matrix into the product of two smaller-sized nonnegative matrices, which has been shown intractable in general. In order to overcome this issue, separability assumption is introduced which assumes all data points are in a conical hull. This assumption makes NMF tractable and is widely used in text analysis and image processing, but still impractical for huge-scale datasets. In this paper, inspired by recent development on dequantizing techniques, we propose a new classical algorithm for separable NMF problem. Our new algorithm runs in polynomial time in the rank and logarithmic in the size of input matrices, which achieves an exponential speedup in the low-rank setting. Copyright © 2019, The Authors. All rights reserved.

关键词： Non-negative matrix factorization

Graph based Tensor Recovery for Accurate Internet Anomaly Detection

学校读者我要写书评

暂无评论

Graph based Tensor Recovery for Accurate Internet Anomaly De...

2018 IEEE Conference on Computer Communications, INFOCOM 2018

作者： Xie, Kun Li, Xiaocan Wang, Xin Xie, Gaogang Wen, Jigang Zhang, Dafang College of Computer Science and Electronics Engineering Hunan University China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China Department of Electrical and Computer Engineering State University of New York at Stony Brook United States Institute of Computing Technology Chinese Academy of Sciences China

ISBN: (纸本)9781538641286

Detecting anomalous traffic is a crucial task of managing networks. Many anomaly detection algorithms have been proposed recently. However, constrained by their matrix-based traffic data model, existing algorithms often suffer from low detection accuracy. To fully utilize the multi-dimensional information hidden in the traffic data, this paper takes an initiative to investigate the potential and methodologies of performing tensor factorization for more accurate Internet anomaly detection. Only considering the low-rank linearity features hidden in the data, current tensor factorization techniques would result in low anomaly detection accuracy. We propose a novel Graph-based Tensor Recovery model (Graph-TR) to well explore both low rank linearity features as well as the non-linear proximity information hidden in the traffic data for better anomaly detection. We encode the non-linear proximity information of the traffic data by constructing nearest neighbor graphs and incorporate this information into the tensor factorization using the graph Laplacian. Moreover, to facilitate the quick building of neighbor graph, we propose a nearest neighbor searching algorithm with the simple locality-sensitive hashing (LSH). We have conducted extensive experiments using Internet traffic trace data Abilene and GEANT. Compared with the state of art algorithms on matrix-based anomaly detection and tensor recovery approach, our Graph-Trcan achieve significantly lower False Positive Rate and higher True Positive Rate. © 2018 IEEE.

关键词： Anomaly detection