检索结果-内蒙古大学图书馆

A Distributed Privacy-Preserving Learning Dynamics in General Social Networks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Tao, Youming Chen, Shuzhen Li, Feng Yu, Dongxiao Yu, Jiguo Sheng, Hao School of Computer Science and Technology Shandong University Qingdao266237 China Big Data Institute Qilu University of Technology Jinan250353 China State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

In this paper, we study a distributed privacy-preserving learning problem in social networks with general topology. The agents can communicate with each other over the network, which may result in privacy disclosure, since the trustworthiness of the agents cannot be guaranteed. Given a set of options which yield unknown stochastic rewards, each agent is required to learn the best one, aiming at maximizing the resulting expected average cumulative reward. To serve the above goal, we propose a four-staged distributed algorithm which efficiently exploits the collaboration among the agents while preserving the local privacy for each of them. In particular, our algorithm proceeds iteratively, and in every round, each agent i) randomly perturbs its adoption for the privacy-preserving purpose, ii) disseminates the perturbed adoption over the social network in a nearly uniform manner through random walking, iii) selects an option by referring to the perturbed suggestions received from its peers, and iv) decides whether or not to adopt the selected option as preference according to its latest reward feedback. Through solid theoretical analysis, we quantify the trade-off among the number of agents (or communication overhead), privacy preserving and learning utility. We also perform extensive simulations to verify the efficacy of our proposed social learning algorithm. Copyright © 2020, The Authors. All rights reserved.

关键词： Iterative methods

A Regularized LSTM Network for Short-Term Traffic Flow Prediction

学校读者我要写书评

暂无评论

A Regularized LSTM Network for Short-Term Traffic Flow Predi...

International Conference on Information Science and Control engineering (ICISCE)

作者： Zhan Wang Rui Zhu Ming Zheng Xuebin Jia Runfang Wang Tong Li National Pilot School of software Yunnan University School of Big Data Yunnan Agricultural University The Key Laboratory for Software Engineering of Yunnan Province

ISBN: (数字)9781728157122

ISBN: (纸本)9781728157139

Short-term traffic flow forecast plays an important role in intelligent transportation systems. Existing traffic flow prediction model used deep layer neural network, which can't prevent over fitting, resulting in performance loss and lack of generalization ability. We propose a regularized LSTM model that fused recurrent dropout and max-norm weight constraint. We apply recurrent dropout to the recurrent connections of LSTM network, and use max-norm weight constraint to arrest the input weights not to grow very large. Simultaneously, we merge ADAM optimizer into our model. We use three datasets from different countries. In order to compare with the other researchers in the field of traffic flow prediction, we introduce same features and perform the same time interval prediction task. The experiment results show that our model has the lowest root mean square error and mean absolute error than the basic LSTM and other machine learning model including BP neural network, RNN, stacked autoencoder.

关键词：

Harmonia: A high throughput B+tree for GPUs 19

学校读者我要写书评

暂无评论

Harmonia: A high throughput B+tree for GPUs

24th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2019

作者： Yan, Zhaofeng Lin, Yuzhe Peng, Lu Zhang, Weihua Software School Fudan University China Shanghai Key Laboratory of Data Science Fudan University China Shanghai Institute of Intelligent Electronics and Systems Shanghai China Division of Electrical and Computer Engineering Louisiana State University United States

ISBN: (纸本)9781450362252

B+tree is one of the most important data structures and has been widely used in different fields. With the increase of concurrent queries and data-scale in storage, designing an eficient B+tree structure has become critical. Due to abundant computation resources, GPUs provide potential opportunities to achieve high query throughput for B+tree. However, prior methods cannot achieve satisfactory performance results due to low resource utilization and poor memory performance. In this paper, we first identify the gaps between B+tree and GPUs. Concurrent B+tree queries involve many global memory accesses and different divergences, which mismatch with GPU features. Based on this observation, we propose Harmonia, a novel B+tree structure to bridge the gap. In Harmonia, a B+tree structure is divided into a key region and a child region. The key region stores the nodes with its keys in a breadth-first order. The child region is organized as a prefix-sum array, which only stores each node's first child index in the key region. Since the prefix-sum child region is small and the children's index can be retrieved through index computations, most of it can be stored in on-chip caches, which can achieve good cache locality. To make it more eficient, Harmonia also includes two optimizations: partially-sorted aggregation and narrowed thread-group traversal, which can mitigate memory and warp divergence and improve resource utilization. Evaluations on a TITAN V GPU show that Harmonia can achieve up to 3.6 billion queries per second, which is about 3.4X faster than that of HB+Tree [39], a recent state-of-the-art GPU solution. © 2019 Association for Computing Machinery.

关键词： Trees (mathematics)

Collusion-Proof Result Inference in Crowdsourcing

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2018年第2期33卷 351-365页

作者： Peng-Peng Chen Hai-Long Sun Yi-Li Fang Jin-Peng Huai State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing 100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing 100191 China

In traditional crowdsourcing, workers are expected to provide independent answers to tasks so as to ensure the diversity of answers. However, recent studies show that the crowd is not a collection of independent workers, but instead that workers communicate and collaborate with each other. To pursue more rewards with little effort, some workers may collude to provide repeated answers, which will damage the quality of the aggregated results. Nonetheless, there are few efforts considering the negative impact of collusion on result inference in crowdsourcing. In this paper, we are specially concerned with the Collusion-Proof result inference problem for general crowdsourcing tasks in public platforms. To that end, we design a metric, the worker performance change rate, to identify the colluded answers by computing the difference of the mean worker performance before and after removing the repeated answers. Then we incorporate the collusion detection result into existing result inference methods to guarantee the quality of the aggregated results even with the occurrence of collusion behaviors. With real-world and synthetic datasets, we conducted an extensive set of evaluations of our approach. The experimental results demonstrate the superiority of our approach in comparison with the state-of-the-art methods.

关键词： crowdsourcing quality control collusion collaborative crowdsourcing result inference

Deep Domain Adaptation for Pavement Crack Detection

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Huijun Yang, Chunhua Li, Ao Huang, Sheng Feng, Xin Ruan, Zhimin Ge, Yongxin College of Computer Science Chongqing University Chongqing400044 China School of Big Data and Software Engineering Chongqing University Chongqing401331 China Chongqing City Management College Chongqing401331 China Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education Chongqing University Chongqing400044 China College of Computer Science And Engineering Chongqing University of Technology Chongqing400054 China Co. Ltd Chongqing400060 China

Deep learning-based pavement cracks detection methods often require large-scale labels with detailed crack location information to learn accurate predictions. In practice, however, crack locations are very difficult to be manually annotated due to various visual patterns of pavement crack. In this paper, we propose a Deep Domain Adaptation-based Crack Detection Network (DDACDN), which learns domain invariant features by taking advantage of the source domain knowledge to predict the multi-category crack location information in the target domain, where only image-level labels are available. Specifically, DDACDN first extracts crack features from both the source and target domain by a two-branch weights-shared backbone network. And in an effort to achieve the cross-domain adaptation, an intermediate domain is constructed by aggregating the three-scale features from the feature space of each domain to adapt the crack features from the source domain to the target domain. Finally, the network involves the knowledge of both domains and is trained to recognize and localize pavement cracks. To facilitate accurate training and validation for domain adaptation, we use two challenging pavement crack datasets CQU-BPDD and RDD2020. Furthermore, we construct a new large-scale Bituminous Pavement Multi-label Disease dataset named CQU-BPMDD, which contains 38994 high-resolution pavement disease images to further evaluate the robustness of our model. Extensive experiments demonstrate that DDACDN outperforms state-of-the-art pavement crack detection methods in predicting the crack location on the target domain. Copyright © 2021, The Authors. All rights reserved.

关键词： Crack detection

A robust and generalized framework for adversarial graph embedding

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Jianxin Fu, Xingcheng Peng, Hao Wang, Senzhang Zhu, Shijie Sun, Qingyun Yu, Philip S. He, Lifang Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100083 China State Key Laboratory of Software Development Environment Beihang University Beijing100083 China School of Computer Science and Engineering Central South University Changsha410083 China Department of Computer Science University of Illinois at Chicago ChicagoIL60607 United States Department of Computer Science and Engineering Lehigh University BethlehemPA18015 United States

Graph embedding is essential for graph mining tasks. With the prevalence of graph data in real-world applications, many methods have been proposed in recent years to learn high quality graph embedding vectors various types of graphs. However, most existing methods usually randomly select the negative samples from the original graph to enhance the training data without considering the noise. In addition, most of these methods only focus on the explicit graph structures and cannot fully capture complex semantics of edges such as various relationships or asymmetry. In order to address these issues, we propose a robust and generalized framework for adversarial graph embedding based on generative adversarial networks. Inspired by generative adversarial network, we propose a robust and generalized framework for adversarial graph embedding, named AGE. AGE generates the fake neighbor nodes as the enhanced negative samples from the implicit distribution, and enables the discriminator and generator to jointly learn each node's robust and generalized representation. Based on this framework, we propose three models to handle three types of graph data and derive the corresponding optimization algorithms, i.e., UG-AGE and DG-AGE for undirected and directed homogeneous graphs, respectively, and HIN-AGE for heterogeneous information networks. Extensive experiments show that our methods consistently and significantly outperform existing state-of-the-art methods across multiple graph mining tasks, including link prediction, node classification, and graph reconstruction. Copyright © 2021, The Authors. All rights reserved.

关键词： Directed graphs

Identity-aware attribute recognition via real-time distributed inference in mobile edge clouds

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Xu, Zichuan Zhou, Pan Wu, Jiangkai Ren, Jiankang Xia, Qiufen Liang, Huizhi Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province School of Software Dalian University of Technology Dalian China Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China School of Software Dalian University of Technology Dalian China School of Computer Science Dalian University of Technology Dalian China Key Laboratory for Ubiquitous Network Service Software of Liaoning Province International School of Information Science and Engineering Dalian University of Technology Dalian China Department of Computer Science University of Reading Reading United Kingdom

With the development of deep learning technologies, attribute recognition and person re-identification (re-ID) have attracted extensive attention and achieved continuous improvement via executing computing-intensive deep neural networks in cloud datacenters. However, the datacenter deployment cannot meet the real-time requirement of attribute recognition and person re-ID, due to the prohibitive delay of backhaul networks and large data transmissions from cameras to datacenters. A feasible solution thus is to employ mobile edge clouds (MEC) within the proximity of cameras and enable distributed inference. In this paper, we design novel models for pedestrian attribute recognition with re-ID in an MEC-enabled camera monitoring system. We also investigate the problem of distributed inference in the MEC-enabled camera network. To this end, we first propose a novel inference framework with a set of distributed modules, by jointly considering the attribute recognition and person re-ID. We then devise a learning-based algorithm for the distributions of the modules of the proposed distributed inference framework, considering the dynamic MEC-enabled camera network with uncertainties. We finally evaluate the performance of the proposed algorithm by Copyright © 2020, The Authors. All rights reserved.

关键词： Mobile edge computing

Robust Bidirectional Generative Network For Generalized Zero-Shot Learning

学校读者我要写书评

暂无评论

Robust Bidirectional Generative Network For Generalized Zero...

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yun Xing Sheng Huang Luwen Huangfu Feiyu Chen Yongxin Ge Ministry of Education Key Laboratory of Dependable Service Computing in Cyber Physical Society School of Big Data and Software Engineering at Chongqing University Chongqing P.R.China Fowler College of Business at San Diego State University San Diego USA

ISBN: (数字)9781728113319

ISBN: (纸本)9781728113326

In this work, we propose a novel generative approach named Robust Bidirectional Generative Network (RBGN) based on Conditional Generative Adversarial Network (CGAN) for Generalized Zero-shot Learning (GZSL). RBGN employs the adversarial attack to train a more rigorous discriminator, thus enhancing the generalizability and robustness of the feature generator under minimax strategy. Moreover, RBGN decodes the generated visual features back to their semantic representations to further improve the representational ability of generated visual features and alleviate the hubness problem. The experimental results of GZSL on four datasets, i.e. CUB, SUN, AWA1, AWA2, demonstrate that our model achieves competitive performance compared to state-of-the-art approaches and owns better generalizability to the unseen classes over conventional generative GZSL models. Further robustness analysis also validates the strong robustness of our model to the different types of semantic disturbance.

关键词： Semantics Visualization Robustness Generators Training Decoding Gallium nitride

Rely-Guarantee Reasoning about Messaging System for Autonomous Vehicles

学校读者我要写书评

暂无评论

Rely-Guarantee Reasoning about Messaging System for Autonomo...

Theoretical Aspects of software engineering (TASE)

作者： Wenjing Xu Yongwang Zhao Dianfu Ma YuXin Zhang Qian Xiao State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang Univerisity Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China State Key Laboratory of Automotive Simulation and Control College of Automotive Engineering Jilin University Jilin China School of Computer Science and Technology Guizhou University Guiyang China

Messaging system as a communicating infrastructure is a safety-critical component of autonomous vehicles. For the purpose of safety certification of Level 4 autonomous driving systems, its necessary to provide a formally verified specification of messaging systems. This paper presents a realistic case study using the PiCore rely-guarantee framework to formally verify the DGPS (Differential Global Positioning System) of UISEE autonomous driving systems. We first create an axiom model of messaging systems by extending PiCore, which is reusable for concrete applications. The model supports dynamic configuration of message buffers as well as the automatic generation of the rely and guarantee conditions for compositional reasoning. It is instantiated when developing the formal specification of DGPS. Then, we use the rely-guarantee proof system of PiCore to verify the functional correctness and invariant of DGPS. The specification and its proof provide a strong evidence for the ongoing safety certification of DGPS.

关键词： Cognition Safety Formal specifications Vehicle dynamics Autonomous vehicles Certification Global Positioning System