检索结果-内蒙古大学图书馆

Graph-Induced Contrastive Learning for Intra-Camera Supervised Person Re-Identification

IEEE ACCESS 2021年 9卷 20850-20860页

作者： Wang, Menglin Lai, Baisheng Huang, Jianqiang Gong, Xiaojin Hua, Xian-Sheng Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou 310027 Peoples R China Alibaba Grp Hangzhou 311121 Peoples R China

Intra-camera supervision (ICS) for person re-identification (Re-ID) assumes that identity labels are independently annotated within each camera view and no inter-camera identity association is labeled. It is a new setting proposed recently to reduce the burden of annotation while expect to maintain desirable Re-ID performance. However, the lack of inter-camera labels makes the ICS Re-ID problem much more challenging than the fully supervised counterpart. By investigating the characteristics of ICS, this article proposes a graph-induced contrastive learning (GCL) approach to address this issue. More specifically, we first formulate the cross-camera ID association task as a graph partitioning problem subjected to ICS-specific constraints and design a greedy agglomeration algorithm to solve it. Then, we propose a graph-induced contrastive loss that unifies both intra- and inter-camera learning into a contrastive learning framework to learn a Re-ID model. The cross-camera ID association step and the Re-ID model contrastive learning step are alternatively iterated, by which we progressively obtain a highly discriminative Re-ID model. Extensive experiments on three large-scale datasets show that our approach outperforms all previous ICS works. Especially, it gains 15.7% Rank-1 and 14.3% mAP improvements on the challenging MSMT17 dataset. Moreover, our approach performs even comparable to state-of-the-art fully supervised methods on all of the three datasets.

关键词： Cameras Integrated circuits Task analysis Reliability partitioning algorithms Feature extraction Annotations Intra-camera supervision person re-identification contrastive learning graph partition

来源：评论

学校读者我要写书评

暂无评论

On the Convergence Behavior of Partitioned-Block Frequency-Domain Adaptive Filters

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2021年 69卷 4906-4920页

作者： Yang, Feiran Enzner, Gerald Yang, Jun Chinese Acad Sci Inst Acoust State Key Lab Acoust Beijing 100190 Peoples R China Carl von Ossietzky Univ Oldenburg Dept Med Phys & Acoust D-26111 Oldenburg Germany Chinese Acad Sci Inst Acoust Key & Aboratory Noise & Vibrat Res Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

Partitioned-block frequency-domain adaptive filter (PBFDAF) algorithms have become very popular, in particular, for acoustic signal processing. However, the stochastic behavior of PBFDAFs has not been extensively examined. This paper presents a comprehensive statistical analysis for a family of the overlap-save PBFDAF algorithms with 50% overlap, including the transient and steady-state performance. The frequency-domain equations of the PBFDAFs are transformed into the time-domain counterparts, which allows us to carry out the analysis completely in the time domain. By means of the independence assumption and vectorization operation, theoretical models for the mean and mean-square behavior of the PBFDAF algorithms are established without restricting the distribution of the inputs to being Gaussian. Specifically, the mean weight behavior and corresponding steady-state solution are provided. Closed-form expressions for the mean-square deviation (MSD) and mean-square error (MSE) are derived. The upper bound on the step size for the mean and mean-square stability of the PBFDAFs is specified. The theoretical model presents new insights into the convergence properties of the PBFDAFs with a sufficient number of coefficients. It was revealed that both the constrained and unconstrained PBFDAFs converge to the Wiener solution. However, the mean weight vector of the unconstrained PBFDAF algorithms cannot converge to the true solution for any inputs, while that of the constrained version can. The presented theory explains why the steady-state MSD of the unconstrained PBFDAF algorithm is larger than that of the constrained version but their minimum MSE is the same. Monte Carlo simulations provide very good support for our theory.

关键词： Signal processing algorithms Steady-state Convergence Time-domain analysis partitioning algorithms Transient analysis Approximation algorithms Adaptive filtering frequency domain PBFDAF transient behavior steady-state solution

来源：评论

学校读者我要写书评

暂无评论

Efficient Data Loader for Fast Sampling-Based GNN Training on Large Graphs

引用

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS 2021年第10期32卷 2541-2556页

作者： Bai, Youhui Li, Cheng Lin, Zhiqi Wu, Yufei Miao, Youshan Liu, Yunxin Xu, Yinlong Univ Sci & Technol China Sch Comp Sci & Technol Hefei 230026 Anhui Peoples R China Microsoft Res Beijing 100080 Peoples R China Anhui Prov Key Lab High Performance Comp Hefei 230026 Anhui Peoples R China

Emerging graph neural networks (GNNs) have extended the successes of deep learning techniques against datasets like images and texts to more complex graph-structured data. By leveraging GPU accelerators, existing frameworks combine mini-batch and sampling for effective and efficient model training on large graphs. However, this setup faces a scalability issue since loading rich vertex features from CPU to GPU through a limited bandwidth link usually dominates the training cycle. In this article, we propose PaGraph, a novel, efficient data loader that supports general and efficient sampling-based GNN training on single-server with multi-GPU. PaGraph significantly reduces the data loading time by exploiting available GPU resources to keep frequently-accessed graph data with a cache. It also embodies a lightweight yet effective caching policy that takes into account graph structural information and data access patterns of sampling-based GNN training simultaneously. Furthermore, to scale out on multiple GPUs, PaGraph develops a fast GNN-computation-aware partition algorithm to avoid cross-partition access during data-parallel training and achieves better cache efficiency. Finally, it overlaps data loading and GNN computation for further hiding loading costs. Evaluations on two representative GNN models, GCN and GraphSAGE, using two sampling methods, Neighbor and Layer-wise, show that PaGraph could eliminate the data loading time from the GNN training pipeline, and achieve up to 4.8x performance speedup over the state-of-the-art baselines. Together with preprocessing optimization, PaGraph further delivers up to 16.0x end-to-end speedup.

关键词： Training Graphics processing units Loading Computational modeling Load modeling partitioning algorithms Deep learning Graph neural network cache large graph graph partition pipeline multi-GPU

来源：评论

学校读者我要写书评

暂无评论

Specification-Guided Verification and Abstraction Refinement of Mixed Monotone Stochastic Systems

引用

IEEE TRANSACTIONS ON AUTOMATIC CONTROL 2021年第7期66卷 2975-2990页

作者： Dutreix, Maxence Coogan, Samuel Georgia Inst Technol Sch Elect & Comp Engn Atlanta GA 30332 USA Georgia Inst Technol Sch Civil & Environm Engn Atlanta GA 30332 USA

This article addresses the problem of verifying discrete-time stochastic systems against omega-regular specifications using finite-state abstractions. Omega-regular properties allow specifying complex behavior and encompass, for example, linear temporal logic. We focus on a class of systems with mixed monotone dynamics. This class is shown to be amenable to efficient reachable set computation and models a wide range of physically relevant systems. In general, finite-state abstractions of continuous state stochastic systems give rise to augmented Markov chains wherein the probabilities of transition between states are restricted to an interval. We present a procedure to compute a finite-state interval-valued Markov chain (IMC) abstraction of discrete-time, mixed monotone stochastic systems subject to affine disturbances given a rectangular partition of the state space. Then, we suggest an algorithm for performing verification against omega-regular properties in IMCs. Specifically, we aim to compute bounds on the probability of satisfying a specification from any initial state in the IMC. This is achieved by solving a reachability problem on the sets of so-called winning and losing components in the Cartesian product between the IMC and a Rabin automaton representing the specification. Next, the verification of IMCs may yield a set of states whose acceptance status is undecided with respect to the specification, requiring a refinement of the abstraction. We describe a specification-guided approach that compares the best and worst case behaviors of accepting paths in the IMC and targets the appropriate states accordingly. Finally, we show a case study.

关键词： Stochastic systems Markov processes Computational modeling Automata partitioning algorithms Upper bound Finite-state abstractions interval-valued Markov chains (IMCs) mixed monotone systems stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Qubit Mapping Based on Subgraph Isomorphism and Filtered Depth-Limited Search

引用

IEEE TRANSACTIONS ON COMPUTERS 2021年第11期70卷 1777-1788页

作者： Li, Sanjiang Zhou, Xiangzhen Feng, Yuan Univ Technol Sydney Fac Engn & Informat Technol Ctr Quantum Software & Informat QSI Ultimo NSW 2007 Australia Southeast Univ State Key Lab Millimeter Waves Nanjing 211189 Peoples R China

Mapping logical quantum circuits to Noisy Intermediate-Scale Quantum (NISQ) devices is a challenging problem which has attracted rapidly increasing interests from both quantum and classical computing communities. This article proposes an efficient method by (i) selecting an initial mapping that takes into consideration the similarity between the architecture graph of the given NISQ device and a graph induced by the input logical circuit and (ii) searching, in a filtered and depth-limited way, a most useful swap combination that makes executable as many as possible two-qubit gates in the logical circuit. The proposed circuit transformation algorithm can significantly decrease the number of auxiliary two-qubit gates required to be added to the logical circuit, especially when it has a large number of two-qubit gates. For an extensive benchmark set of 131 circuits and IBM's current premium Q system, viz., IBM Q Tokyo, our algorithm needs, in average, 0.3801 extra two-qubit gates per input two-qubit gate, while the corresponding figures for three state-of-the-art algorithms are 0.4705, 0.8154, and 1.0066, respectively.

关键词： Logic gates Quantum computing Computer architecture partitioning algorithms Machine learning algorithms Heuristic algorithms Google NISQ quantum circuit transformation qubit mapping subgraph isomorphism heuristic search

来源：评论

学校读者我要写书评

暂无评论

Hide and Seek: Outwitting Community Detection algorithms

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2021年第4期8卷 799-808页

作者： Mittal, Shravika Sengupta, Debarka Chakraborty, Tanmoy Indraprastha Inst Informat Technol Delhi Dept Comp Sci & Engn New Delhi 110020 India Indraprastha Inst Informat Technol Dept Computat Biol New Delhi 110020 India

Community affiliation of a node plays an important role in determining its contextual position in the network, which may raise privacy concerns when a sensitive node wants to hide its identity in a network. Oftentimes, a target community seeks to protect itself from adversaries so that its constituent members remain hidden inside the network. The current study focuses on hiding such sensitive communities so that the community affiliation of the targeted nodes can be concealed. This leads to the problem of community deception, which investigates the avenues of minimally rewiring nodes in a network so that a given target community maximally hides from a community detection algorithm (CDA). We formalize the problem of community deception and introduce Network deception using permanence loss (NEURAL), a novel method that greedily optimizes a node-centric objective function to determine the rewiring strategy. Theoretical settings pose a restriction on the number of strategies that can be employed to optimize the objective function, which in turn reduces the overhead of choosing the best strategy from multiple options. We also show that our objective function is submodular and monotone. When tested on both synthetic and seven real-world networks, NEURAL is able to deceive six widely used CDAs. We benchmark its performance with respect to four state-of-the-art methods on four evaluation metrics. In addition, our qualitative analysis on three other attributed real-world networks reveals that NEURAL, quite strikingly, captures important metainformation about edges that otherwise could not be inferred by observing only their topological structures.

关键词： Measurement Linear programming Image edge detection Optimization Social networking (online) partitioning algorithms Information technology Community detection community hiding complex networks permanence

来源：评论

学校读者我要写书评

暂无评论

Maximizing Utilization and Minimizing Migration in Thermal-Aware Energy-Efficient Real-Time Multiprocessor Scheduling

引用

IEEE ACCESS 2021年 9卷 83309-83328页

作者： Elena Rubio-Anguiano, Laura Chils Trabanco, Abel Briz Velasco, Jose Luis Ramirez-Trevino, Antonio CINVESTAV IPN Unidad Guadalajara Zapopan 45019 Mexico Univ Zaragoza I3A DIIS Zaragoza 50018 Spain

This work proposes CAlECs, a clustered scheduling system for MPSoCs subject to thermal and energy constraints. It calculates off-line a cyclic executive honoring temporal and thermal constraints, for a hard real-time (HRT) task set at minimum frequency to reduce consumed energy, minimizing context switches and migrations. It also provides an on-line controller able to manage system and task parametric variations and soft real-time (SRT) tasks, always meeting the HRT task set constraints and the system thermal bound. CAlECS maximizes CPU utilization to help avoid overprovisioning contributing to a low SWaP factor. Its modular design allows the utilization of different modeling and scheduling approaches, and makes the off-line and on-line components independent from each other to better suit the requirements of a specific system. We experimentally show that the cyclic executive provided by CAlECS for HRT task sets outperforms RUN, a reference off-line algorithm in terms of optimal number of context switches.

关键词： Task analysis Processor scheduling Job shop scheduling Context Schedules Real-time systems partitioning algorithms Real-time scheduling clustering algorithms multiprocessors Petri nets control

来源：评论

学校读者我要写书评

暂无评论

Weighted Adaptive Partition for Heterogeneous IoT Data Stream

引用

IEEE INTERNET OF THINGS JOURNAL 2021年第20期8卷 15240-15248页

作者： Zhang, Mengjun Wang, Wei Tianjin Normal Univ Coll Elect & Commun Engn Tianjin 300387 Peoples R China Tianjin Normal Univ Tianjin Key Lab Wireless Mobile Commun & Power Tr Tianjin 300387 Peoples R China

In the past, many researchers used sliding-window mechanism in Internet of Things (IoT) data stream mining, which can divide the incoming large volume data into small segments and improve the information processing rate. With the emergence of heterogeneous IoT data streams, data forms become richer and more diverse. The fusion analysis of multimodality information can improve the accuracy of information processing and network decision-making, because it can make up for the lack of some information in a single-mode data stream. However, the representation of information in different data sources is different, and the amount of information contained in it is distinct. Thus, a weighted adaptive partition algorithm is proposed in this article, which performs a dynamic weighted fusion of multisource heterogeneous IoT data in sliding windows. The article adopts the Gaussian mixture model (GMM) to adaptively determine the weights of each data source, which is calculated based on the judgement confidence of each modal data to the change in data stream. Besides, the probability distribution change detection mechanism based on multimodality restricted Boltzmann machine (multimodality RBM) is proposed, which measures the joint probability distribution by the weighted data's energy value. Finally, according to the energy change rate of the data stream, the size of the window is adjusted adaptively to realize the partition for heterogeneous IoT data stream. The algorithm proposed in this article is verified on the CUAVE data set and the analysis of results shows that the data under adaptive weighted fusion has better performance.

关键词： partitioning algorithms Internet of Things Data mining Classification algorithms Probability distribution Market research Heuristic algorithms Adaptive partition Gaussian mixture model (GMM) multimodality restricted Boltzmann machine (multimodality RBM) sliding window weighted fusion

来源：评论

学校读者我要写书评

暂无评论

Virtual-Voltage Partition-Based Approach to Optimal Transmission Switching

引用

IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY 2021年第3期29卷 1246-1256页

作者： Chang, Chin-Yao Martinez, Sonia Cortes, Jorge Natl Renewable Energy Lab Golden CO 80401 USA Univ Calif San Diego Dept Mech & Aerosp Engn La Jolla CA 92093 USA

This article deals with optimal transmission switching (OTS) problems involving binary decisions about network topology and nonconvex power flow constraints. We adopt a semidefinite programming formulation for the optimal power flow (OPF) problem that, however, remains nonconvex due to the presence of discrete variables and bilinear products between the decision variables. To tackle the latter, we introduce a physically inspired, virtual-voltage approximation that leads to provable lower and upper bounds on the solution of the original problem. To deal with the exponential complexity caused by the discrete variables, we introduce a graph partition-based algorithm that breaks the problem into several parallel mixed-integer subproblems of smaller size. Simulations on the IEEE bus test cases demonstrate the high degree of accuracy and affordable computational requirements of our approach.

关键词： Switches Optimization Upper bound partitioning algorithms Network topology Programming Power transmission lines Graph partitions mixed-integer programming optimal power flow (OPF) optimal transmission switching (OTS) power networks semidefinite programming (SDP)

来源：评论

学校读者我要写书评

暂无评论

An Overview of Fairness in Clustering

引用

IEEE ACCESS 2021年 9卷 130698-130720页

作者： Chhabra, Anshuman Masalkovaite, Karina Mohapatra, Prasant Univ Calif Davis Dept Comp Sci Davis CA 95616 USA Univ Calif Davis Dept Chem Engn Davis CA 95616 USA

Clustering algorithms are a class of unsupervised machine learning (ML) algorithms that feature ubiquitously in modern data science, and play a key role in many learning-based application pipelines. Recently, research in the ML community has pivoted to analyzing the fairness of learning models, including clustering algorithms. Furthermore, research on fair clustering varies widely depending on the choice of clustering algorithm, fairness definitions employed, and other assumptions made regarding models. Despite this, a comprehensive survey of the field does not exist. In this paper, we seek to bridge this gap by categorizing existing research on fair clustering, and discussing possible avenues for future work. Through this survey, we aim to provide researchers with an organized overview of the field, and motivate new and unexplored lines of research regarding fairness in clustering.

关键词： Clustering algorithms Measurement partitioning algorithms Heuristic algorithms Search problems Task analysis Machine learning algorithms Machine learning clustering fairness fair clustering

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：