检索结果-内蒙古大学图书馆

37th International Conference on Machine Learning, ICML 2020

作者： Xiong, Ruibin Yang, Yunchang He, Di Zheng, Kai Zheng, Shuxin Xing, Chen Zhang, Huishuai Lan, Yanyan Wang, Liwei Liu, Tie-Yan CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technolog Chinese Academy of Sciences China University of Chinese Academy of Sciences China Center for Data Science Peking University Beijing Institute of Big Data Research China Key Laboratory of Machine Perception MOE School of EECS Peking University China Microsoft Research College of Computer Science Nankai University China

ISBN: (纸本)9781713821120

The Transformer is widely used in natural language processing tasks. To train a Transformer however, one usually needs a carefully designed learning rate warm-up stage, which is shown to be crucial to the final performance but will slow down the optimization and bring more hyperparameter tunings. In this paper, we first study theoretically why the learning rate warm-up stage is essential and show that the location of layer normalization matters. Specifically, we prove with mean field theory that at initialization, for the original-designed Post-LN Transformer, which places the layer normalization between the residual blocks, the expected gradients of the parameters near the output layer are large. Therefore, using a large learning rate on those gradients makes the training unstable. The warm-up stage is practically helpful for avoiding this problem. On the other hand, our theory also shows that if the layer normalization is put inside the residual blocks (recently proposed as Pre-LN Transformer), the gradients are well-behaved at initialization. This motivates us to remove the warm-up stage for the training of Pre-LN Transformers. We show in our experiments that Pre-LN Transformers without the warm-up stage can reach comparable results with baselines while requiring significantly less training time and hyper-parameter tuning on a wide range of applications. Copyright 2020 by the author(s).

关键词： Mean field theory

来源：评论

学校读者我要写书评

暂无评论

Global-and-Local Collaborative Learning for Co-Salient Object Detection

arXiv

引用

arXiv 2022年

作者： Cong, Runmin Yang, Ning Li, Chongyi Fu, Huazhu Zhao, Yao Huang, Qingming Kwong, Sam The Institute of Information Science Beijing Jiaotong University Beijing100044 China The Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China The Department of Computer Science City University of Hong Kong Hong Kong The School of Computer Science and Engineering Nanyang Technological University Singapore A*STAR Singapore The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China University of Chinese Academy of Sciences Beijing101408 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Peng Cheng Laboratory Shenzhen518055 China The City University of Hong Kong Shenzhen Research Institute Shenzhen51800 China

The goal of co-salient object detection (CoSOD) is to discover salient objects that commonly appear in a query group containing two or more relevant images. Therefore, how to effectively extract inter-image correspondence is crucial for the CoSOD task. In this paper, we propose a global-and-local collaborative learning architecture, which includes a global correspondence modeling (GCM) and a local correspondence modeling (LCM) to capture comprehensive inter-image corresponding relationship among different images from the global and local perspectives. Firstly, we treat different images as different time slices and use 3D convolution to integrate all intra features intuitively, which can more fully extract the global group semantics. Secondly, we design a pairwise correlation transformation (PCT) to explore similarity correspondence between pairwise images and combine the multiple local pairwise correspondences to generate the local inter-image relationship. Thirdly, the inter-image relationships of the GCM and LCM are integrated through a global-and-local correspondence aggregation (GLA) module to explore more comprehensive inter-image collaboration cues. Finally, the intra- and inter-features are adaptively integrated by an intra-and-inter weighting fusion (AEWF) module to learn co-saliency features and predict the co-saliency map. The proposed GLNet is evaluated on three prevailing CoSOD benchmark datasets, demonstrating that our model trained on a small dataset (about 3k images) still outperforms eleven state-of-the-art competitors trained on some large datasets (about 8k̴200k images). © 2022, CC BY-NC-SA.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Exact distributed quantum algorithm for generalized Simon’s problem

arXiv

引用

arXiv 2023年

作者： Li, Hao Qiu, Daowen Luo, Le Mateus, Paulo Institute of Quantum Computing and Computer Theory School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China The Guangdong Key Laboratory of Information Security Technology Sun Yat-sen University 510006 China QUDOOR Technologies Inc. Zhuhai China School of Physics and Astronomy Sun Yat-sen University Zhuhai519082 China Instituto de Telecomunicações Departamento de Matemática Instituto Superior Técnico Av. Rovisco Pais Lisbon1049-001 Portugal

Simon’s problem is one of the most important problems demonstrating the power of quantum algorithms, as it greatly inspired the proposal of Shor’s algorithm. The generalized Simon’s problem is a natural extension of Simon’s problem, and also a special hidden subgroup problem: Given a function f : {0, 1}n → {0, 1}m, with the property that for any x, y ∈ {0, 1}n, there is some unknown hidden subgroup S ≤ 2n such that f(x) = f(y) iff x ⊕ y ∈ S, where |S| = 2k for some 0 ≤ k ≤ n (m ≥ n − k). The goal of generalized Simon’s problem is to find the hidden subgroup S. In this paper, we present two key contributions. Firstly, we characterize the structure of the generalized Simon’s problem in distributed scenario and introduce a corresponding distributed quantum algorithm. Secondly, we refine the algorithm to ensure exactness due to the application of quantum amplitude amplification technique. Our algorithm offers exponential acceleration compared to the distributed classical algorithm. When contrasted with the centralized quantum algorithm for the generalized Simon’s problem, our algorithm’s oracle requires fewer qubits, thus making it easier to be physically implemented. Particularly, the exact distributed quantum algorithm we develop for the generalized Simon’s problem outperforms the best previously proposed distributed quantum algorithm for Simon’s problem in terms of generalizability and exactness. Copyright © 2023, The Authors. All rights reserved.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

An Imbalanced Learning Based Method for Esophageal Squamous Cell Carcinoma (ESCC) Distant Metastasis Predicting 3rd

An Imbalanced Learning Based Method for Esophageal Squamous ...

引用

3rd International Conference on Machine Learning for Cyber security, ML4CS 2020

作者： Li, Xuemei Yang, Bo Peng, Lizhi Li, Baosheng Zhu, Jian Educational Technology Center Shandong College of Traditional Chinese Medicine Yantai264199 China Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan250022 China Department of Radiation Oncology Shandong Cancer Hospital affiliated to Shandong University Jinan250117 China

ISBN: (纸本)9783030624620

Accurately predicting distant metastasis is very important for esophageal squamous cell carcinoma (ESCC) patients, as it is a key evidence to determine the degree of this disease. Traditional metastasis predictions are made by doctors manually, which is time and labor consuming. In recent years, some researchers try to predict ESCC distant metastasis using machine learning techniques. However, they ignored the factor that the problem of predicting ESCC distant metastasis is a highly imbalanced task. In this study, we try to build a new imbalanced learning based ESCC distant metastasis predicting scheme using blood cell analysis testing results. We first extract effective features from blood cell analysis testing data. And then we use over-sampling method to generate new positive instances (instances with ESCC distant metastasis). Finally, we apply k-nearest neighbor (k-NN) algorithms to predict unknown instances. Experimental results show that our method is effective in cases with few positive instances. © 2020, Springer Nature Switzerland AG.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Safeguarding Next Generation Multiple Access Using Physical Layer security Techniques: A Tutorial

arXiv

引用

arXiv 2024年

作者： Lv, Lu Xu, Dongyang Hu, Rose Qingyang Ye, Yinghui Yang, Long Lei, Xianfu Wang, Xianbin Kim, Dong In Nallanathan, Arumugam The State Key Laboratory of Integrated Services Networks Xidian University Xi’an710071 China The School of Information and Communications Engineering Xi’an Jiaotong University Xi’an710049 China The Department of Electrical and Computer Engineering Utah State University LoganUT84322 United States The Shaanxi Key Laboratory of Information Communication Network and Security Xi’an University of Posts & Telecommunications Xi’an710121 China The School of Information Science and Technology Southwest Jiaotong University Chengdu610031 China The Department of Electrical and Computer Engineering Western University LondonONN6A 5B9 Canada The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of School of Electronic Engineering and Computer Science Queen Mary University of London E1 4NS United Kingdom

Driven by the ever-increasing requirements of ultrahigh spectral efficiency, ultra-low latency, and massive connectivity, the forefront of wireless research calls for the design of advanced next generation multiple access schemes to facilitate provisioning of these stringent demands. This inspires the embrace of non-orthogonal multiple access (NOMA) in future wireless communication networks. Nevertheless, the support of massive access via NOMA leads to additional security threats, due to the open nature of the air interface, the broadcast characteristic of radio propagation as well as intertwined relationship among paired NOMA users. To address this specific challenge, the superimposed transmission of NOMA can be explored as new opportunities for security aware design, for example, multiuser interference inherent in NOMA can be constructively engineered to benefit communication secrecy and privacy. The purpose of this tutorial is to provide a comprehensive overview on the state-of-the-art physical layer security techniques that guarantee wireless security and privacy for NOMA networks, along with the opportunities, technical challenges, and future research trends. Copyright © 2024, The Authors. All rights reserved.

关键词： Radio waves

来源：评论

学校读者我要写书评

暂无评论

Learning with multiclass AUC: Theory and algorithms

arXiv

引用

arXiv 2021年

作者： Yang, Zhiyong Xu, Qianqian Bao, Shilong Cao, Xiaochun Huang, Qingming The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China The School of Cyber Security University of Chinese Academy of Sciences Beijing100049 China School of Cyber Science and Technology Sun Yat-sen University Shenzhen518100 China University of Chinese Academy of Sciences Beijing101408 China Peng Cheng Laboratory Shenzhen518055 China

The Area under the ROC curve (AUC) is a well-known ranking metric for problems such as imbalanced learning and recommender systems. The vast majority of existing AUC-optimization-based machine learning methods only focus on binary-class cases, while leaving the multiclass cases unconsidered. In this paper, we start an early trial to consider the problem of learning multiclass scoring functions via optimizing multiclass AUC metrics. Our foundation is based on the M metric, which is a well-known multiclass extension of AUC. We first pay a revisit to this metric, showing that it could eliminate the imbalance issue from the minority class pairs. Motivated by this, we propose an empirical surrogate risk minimization framework to approximately optimize the M metric. Theoretically, we show that: (i) optimizing most of the popular differentiable surrogate losses suffices to reach the Bayes optimal scoring function asymptotically;(ii) the training framework enjoys an imbalance-aware generalization error bound, which pays more attention to the bottleneck samples of minority classes compared with the traditional O(p1/N) result. Practically, to deal with the low scalability of the computational operations, we propose acceleration methods for three popular surrogate loss functions, including the exponential loss, squared loss, and hinge loss, to speed up loss and gradient evaluations. Finally, experimental results on 11 real-world datasets demonstrate the effectiveness of our proposed framework.. © 2021, CC BY.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Respiratory Sound Classification Based on BiGRU-Attention network with XGBoost

Respiratory Sound Classification Based on BiGRU-Attention Ne...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xuesong Zhao Yanbo Shao Juanyun Mai Airu Yin Sihan Xu College of Computer Science Nankai University Tianjin China Tianjin Key Laboratory of Network and Data Security Technology Tianjin China KLMDASR Tianjin China

ISBN: (数字)9781728162157

ISBN: (纸本)9781728162164

In recent years, the mortality rate of respiratory diseases ranks high among the major diseases. Early detection of respiratory diseases is a key factor in reducing the mortality rate and curing diseases. In this paper, we propose the BiGRU Attention-XGBoost model to classify respiratory sounds, in order to assist doctors in the early diagnosis of respiratory diseases. Specifically, we first extract two sets of features, i.e., the time domain and spectral features to encode respiratory sounds. Then, we apply the Gradient Boosting Decision Tree algorithm to select important features for classification. Based on the temporal characteristics of respiratory sounds, we design the BiGRU Attention-XGBoost model to classify them. Finally, to enlarge the training dataset and address the problem of data imbalance, we also implement Griffifin-Lim and WORLD Vocoder, two data augmentation methods. Extensive experiments show the superiority of the proposed model compared to seven state-of the-art models in terms of classification accuracy and Fl-score.

关键词： Feature extraction Mathematical model Hidden Markov models Training Mel frequency cepstral coefficient Time-domain analysis Logic gates

来源：评论

学校读者我要写书评

暂无评论

Cipherchain:A Secure and Efficient Ciphertext Blockchain via mPECK

引用

Journal of Quantum computing 2020年第1期2卷 57-83页

作者： Hailin Chen Gang Xu Yuling Chen Xiubo Chen Yixian Yang Ruibin Fan Kaixiang Zhang Huizhong Li Information Security Center State Key Laboratory of Networking and Switching TechnologyBeijing University of Posts and TelecommunicationsBeijing100876China Guizhou University Sate Key Laboratory of Public Big DataGuizhou550025China North China University of Technology School of Computing Science and TechnologyBeijingChina Webank Shenzhen518000China

Most existing blockchain schemes are based on the design concept“openness and transparency”to realize data security,which usually require transaction data to be presented in the form of ***,it inevitably brings the issues with respect to data privacy and operating *** this paper,we proposed a novel blockchain scheme called Cipherchain,which can process and maintain transaction data in the form of ciphertext while the characteristics of immutability and auditability are *** in our scheme,transactions can be encrypted locally based on a searchable encryption scheme called multi-user public key encryption with conjunctive keyword search(mPECK),and can be accessed by multiple specific participants after appended to the globally consistent distributed *** introducing execution-consensus-update paradigm of transaction flow,Cipherchain cannot only make it possible for transaction data to exist in the form of ciphertext,but also guarantee the overall system performance not greatly affected by cryptographic operations and other local execution *** addition,Cipherchain is a promising scheme to realize the technology combination of“blockchain+cloud computing”and“permissioned blockchain+public blockchain”.

关键词： Blockchain Cipherchain cloud computing mPECK

来源：评论

学校读者我要写书评

暂无评论

Adversity-Based Social Circles Inference via Context-Aware Mobility

Adversity-Based Social Circles Inference via Context-Aware M...

引用

GLOBECOM 2020 - 2020 IEEE Global Communications Conference

作者： Qiang Gao Fan Zhou Goce Trajcevski Fengli Zhang Xucheng Luo Network and Data Security Key Laboratory of Sichuan Province China University of Electronic Science and Technology of China China Iowa State University Ames USA

ISBN: (数字)9781728182988

ISBN: (纸本)9781728182995

The ubiquity of mobile devices use has generated huge volumes of location-aware contextual data, providing opportunities enriching various location-based social network (LBSN) applications - e.g., trip recommendation, ride-sharing allocation and taxi demand prediction etc. Trajectory-based social circle inference (TSCI), which aims at inferring the social relationships among users based on the human mobility data, has received great attention in recent years due to its importance in many LBSN applications. However, existing solutions suffer from three key challenges, including (1) lack of modeling contextual feature in user check-ins; (2) cannot capture the structural information in user motion patterns; (3) and fail to consider the underlying mobility distribution. In this paper, we propose a novel framework ASCI-CAM (Adversity-based Social Circles Inference via Context-Aware Mobility) to address the above challenges. ASCI-CAM is a graph-based model taking into account the contextual information associated with check-ins which, combined with an attentive auto-encoder, allows for semantic trajectory representation. We regularize the learned trajectory embedding with an adversarial learning procedure, which allows us to better understand the user mobility patterns and personalized trajectory distribution. Our extensive experiments on real-world mobility datasets demonstrate that our model achieves significant improvement over the state-of-the-art baselines.

关键词： Trajectory Social networking (online) Training Task analysis Semantics Logic gates Training data

来源：评论

学校读者我要写书评

暂无评论

SPECBOX: A label-based transparent speculation scheme against transient execution attacks

arXiv

引用

arXiv 2021年

作者： Tang, Bowen Wu, Chenggang Wang, Zhe Jia, Lichen Yew, Pen-Chung Cheng, Yueqiang Zhang, Yinqian Wang, Chenxi Xu, Guoqing Harry State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China University of the Chinese Academy of Sciences China University of Minnesota Twin Cities United States NIO Security Research United States Southern University of Science and Technology China University of California Los Angeles United States

Speculative execution techniques have been a cornerstone of modern processors to improve instruction-level parallelism. However, recent studies showed that this kind of techniques could be exploited by attackers to leak secret data via transient execution attacks, such as Spectre. Many defenses are proposed to address this problem, but they all face various challenges: (1) Tracking data flow in the instruction pipeline could comprehensively address this problem, but it could cause pipeline stalls and incur high performance overhead;(2) Making side effect of speculative execution imperceptible to attackers, but it often needs additional storage components and complicated data movement operations. In this paper, we propose a label-based transparent speculation scheme called SPECBOX. It dynamically partitions the cache system to isolate speculative data and non-speculative data, which can prevent transient execution from being observed by subsequent execution. Moreover, it uses thread ownership semaphores to prevent speculative data from being accessed across cores. In addition, SPECBOX also enhances the auxiliary components in the cache system against transient execution attacks, such as hardware prefetcher. Our security analysis shows that SPECBOX is secure and the performance evaluation shows that the performance overhead on SPEC CPU 2006 and PARSEC-3.0 benchmarks is small. Copyright © 2021, The Authors. All rights reserved.

关键词： Digital storage

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：