检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

329 篇 会议
9 篇 期刊文献
2 册 图书

馆藏范围

340 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

219 篇 工学
- 190 篇 计算机科学与技术...
- 104 篇 软件工程
- 48 篇 信息与通信工程
- 33 篇 电气工程
- 17 篇 电子科学与技术（可...
- 14 篇 控制科学与工程
- 9 篇 机械工程
- 9 篇 仪器科学与技术
- 6 篇 动力工程及工程热...
- 4 篇 力学（可授工学、理...
- 4 篇 建筑学
- 4 篇 测绘科学与技术
- 4 篇 环境科学与工程（可...
- 4 篇 网络空间安全
- 3 篇 材料科学与工程（可...
- 3 篇 土木工程
- 3 篇 生物工程
63 篇 理学
- 41 篇 数学
- 10 篇 系统科学
- 8 篇 统计学（可授理学、...
- 5 篇 物理学
- 4 篇 生物学
- 3 篇 化学
- 3 篇 大气科学
- 2 篇 海洋科学
37 篇 管理学
- 29 篇 管理科学与工程(可...
- 18 篇 工商管理
- 10 篇 图书情报与档案管...
3 篇 经济学
- 3 篇 应用经济学
3 篇 教育学
- 3 篇 教育学
2 篇 法学
1 篇 医学

主题

30 篇 distributed comp...
28 篇 cloud computing
23 篇 distributed comp...
15 篇 computer science
15 篇 fault tolerance
13 篇 computational mo...
11 篇 protocols
9 篇 computer archite...
8 篇 concurrent compu...
8 篇 distributed data...
7 篇 internet of thin...
7 篇 scalability
7 篇 deep learning
7 篇 algorithms
7 篇 resource managem...
7 篇 costs
7 篇 edge computing
7 篇 delay
7 篇 training
6 篇 quantum computin...

机构

3 篇 college of compu...
2 篇 computer enginee...
2 篇 microsoft corp r...
2 篇 école polytechni...
2 篇 department of co...
2 篇 massachusetts in...
2 篇 technion haifa
2 篇 iit madras
2 篇 res & acad comp ...
2 篇 univ toronto dep...
2 篇 virginia tech bl...
2 篇 argonne national...
2 篇 department of di...
2 篇 cornell univ ith...
2 篇 univ connecticut...
2 篇 lawrence livermo...
2 篇 etri daejeon
2 篇 oak ridge natl l...
2 篇 tomsk polytech u...
2 篇 etri daejeon rep...

作者

3 篇 peleg david
3 篇 schulz martin
3 篇 wattenhofer roge...
3 篇 de supinski bron...
3 篇 gilbert seth
3 篇 hadzilacos vasso...
2 篇 hong-linh truong
2 篇 subramoni hari
2 篇 claudia campolo
2 篇 karp richard m.
2 篇 fiat amos
2 篇 floriano de rang...
2 篇 g. spezzano
2 篇 mauro tropea
2 篇 rabani yuval
2 篇 bartal yair
2 篇 dongarra jack
2 篇 awerbuch baruch
2 篇 e. greco
2 篇 nicolae bogdan

语言

337 篇 英文
2 篇 中文
1 篇 其他

检索条件"任意字段=24th Symposium on Principles of Distributed Computing"

共 340 条记录，以下是61-70 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

DeepVM: Integrating Spot and On-Demand VMs for Cost-Efficient Deep Learning Clusters in the Cloud

DeepVM: Integrating Spot and On-Demand VMs for Cost-Efficien...

引用

IEEE/ACM International symposium on Cluster computing and the Grid (CCGRID)

作者： Yoochan Kim Kihyun Kim Yonghyeon Cho Jinwoo Kim Awais Khan Ki-Dong Kang Baik-Song An Myung-Hoon Cha Hong-Yeon Kim Youngjae Kim Dept. of Computer Science and Engineering Sogang University Seoul Republic of Korea LG Electronics Oak Ridge National Laboratory TN USA ETRI Daejeon Republic of Korea

ISBN: (数字)9798350395662

ISBN: (纸本)9798350395679

distributed Deep Learning (DDL), as a paradigm, dictates the use of GPU-based clusters as the optimal infrastructure for training large-scale Deep Neural Networks (DNNs). However, the high cost of such resources makes them inaccessible to many users. Public cloud services, particularly Spot Virtual Machines (VMs), offer a cost-effective alternative, but their unpredictable availability poses a significant challenge to the crucial checkpointing process in DDL. To address this, we introduce DeepVM, a novel solution that recommends cost-effective cluster configurations by intelligently balancing the use of Spot and On-Demand VMs. DeepVM leverages a four-stage process that analyzes instance performance using the FLOPP (FLoating-point Operations Per Price) metric, performs architecture-level analysis with linear programming, and identifies the optimal configuration for the user-specific needs. Extensive simulations and real-world deployments in the AWS environment demonstrate that DeepVM consistently outperforms other policies, reducing training costs and overall makespan. By enabling cost-effective checkpointing with Spot VMs, DeepVM opens up DDL to a wider range of users and facilitates a more efficient training of complex DNNs.

关键词： Training Deep learning Checkpointing Measurement Cloud computing Costs Artificial neural networks Linear programming

来源：评论

学校读者我要写书评

暂无评论

Approximate Byzantine Fault-Tolerance in distributed Optimization 21

Approximate Byzantine Fault-Tolerance in Distributed Optimiz...

引用

40th ACM SIGACT-SIGOPS symposium on principles of distributed computing (PODC)

作者： Liu, Shuo Gupta, Nirupam Vaidya, Nitin H. Georgetown Univ Washington DC 20057 USA Ecole Polytech Fed Lausanne EPFL Lausanne Switzerland

ISBN: (纸本)9781450385480

this paper considers the problem of Byzantine fault-tolerance in distributed multi-agent optimization. In this problem, each agent has a local cost function, and in the fault-free case, the goal is to design a distributed algorithm that allows all the agents to find a minimum point of all the agents' aggregate cost function. We consider a scenario where some agents might be Byzantine faulty that renders the original goal of computing a minimum point of all the agents' aggregate cost vacuous. A more reasonable objective for an algorithm in this scenario is to allow all the non-faulty agents to compute the minimum point of only the non-faulty agents' aggregate cost. Prior work [24] shows that if there are up to f (out of n) Byzantine agents then a minimum point of the non-faulty agents' aggregate cost can be computed exactly if and only if the non-faulty agents' costs satisfy a certain redundancy property called 2f -redundancy. However, 2f-redundancy is an ideal property that can be satisfied only in systems free from noise or uncertainties, which can make the goal of exact fault-tolerance unachievable in some applications. thus, we introduce the notion of (f, epsilon)-resilience, a generalization of exact fault-tolerance wherein the objective is to find an approximate minimum point of the non-faulty aggregate cost, with c accuracy. this approximate fault-tolerance can be achieved under a weaker condition that is easier to satisfy in practice, compared to 2f-redundancy. We obtain necessary and sufficient conditions for achieving (f, epsilon)-resilience characterizing the correlation between relaxation in redundancy and approximation in resilience. In case when the agents' cost functions are differentiable, we obtain conditions for (f, epsilon)-resilience of the distributed gradient-descent method when equipped with robust gradient aggregation;such as comparative gradient elimination or coordinate-wise trimmed mean.

关键词： distributed optimization Approximate fault-tolerance distributed gradient-descent

来源：评论

学校读者我要写书评

暂无评论

STEM Educational Game "Young Engineer" to Improve the Digital Competence of Students

STEM Educational Game "Young Engineer" to Improve the Digita...

引用

International symposium on INFOTEH-JAHORINA (INFOTEH)

作者： Aneliya Ivanova Diyan Yordanov Department of Computing University of Ruse Ruse Bulgaria Software Development Ideas4web Ltd Ruse Bulgaria

ISBN: (数字)9798331515799

ISBN: (纸本)9798331515805

In a time when digital competencies become even more important, among the students prepared to be future computer systems and technology engineers, a steady trend of decreasing interest in computer hardware has been observed. It looks like the predictions from the early 21st century that the children of the digital generation would be more likely to use digital technologies than to create them have turned out to be true. But the training of engineers in this field requires knowledge of at least the principles of Boolean logic, the basic logic gates, and the basic sequential and combinational circuits - the so-called "glue" logic because the lack of elementary knowledge in this area makes it difficult to study and design more complex digital systems. Interest in this subject should be encouraged at school age by appropriately introducing the "glue" logic to the students. STEM education is beginning to be massively applied in the school educational system but studying basic logic circuits and devices is weakly, let's say not at all, being presented within the abundance and variety of STEM lessons. the development of a STEM educational game for learning the principle of operation of basic logic gates and how they work together, connected in a circuit diagram, will contribute to increasing the interest in digital logic devices, and hence to easier teaching at university courses related to the design of various digital systems.

关键词： Knowledge engineering Visualization Codes Digital systems Games Logic gates Market research Libraries Logic Integrated circuit modeling

来源：评论

学校读者我要写书评

暂无评论

Efficient Data-Parallel Continual Learning with Asynchronous distributed Rehearsal Buffers

Efficient Data-Parallel Continual Learning with Asynchronous...

引用

IEEE/ACM International symposium on Cluster computing and the Grid (CCGRID)

作者： thomas Bouvier Bogdan Nicolae Hugo Chaugier Alexandru Costan Ian Foster Gabriel Antoniu Inria CNRS IRISA University of Rennes Argonne National Laboratory

ISBN: (数字)9798350395662

ISBN: (纸本)9798350395679

Deep learning has emerged as a powerful method for extracting valuable information from large volumes of data. However, when new training data arrives continuously (i.e., is not fully available from the beginning), incremental training suffers from catastrophic forgetting (i.e., new patterns are reinforced at the expense of previously acquired knowledge). Training from scratch each time new training data becomes available would result in extremely long training times and massive data accumulation. Rehearsal-based continual learning has shown promise for addressing the catastrophic forgetting challenge, but research to date has not addressed performance and scalability. To fill this gap, we propose an approach based on a distributed rehearsal buffer that efficiently complements data-parallel training on multiple GPUs, allowing us to achieve short runtime and scalability while retaining high accuracy. It leverages a set of buffers (local to each GPU) and uses several asynchronous techniques for updating these local buffers in an embarrassingly parallel fashion, all while handling the communication overheads necessary to augment input mini-batches (groups of training samples fed to the model) using unbiased, global sampling. In this paper we explore the benefits of this approach for classification models. We run extensive experiments on up to 128 GPUs of the thetaGPU supercomputer to compare our approach with baselines representative of training-from-scratch (the upper bound in terms of accuracy) and incremental training (the lower bound). Results show that rehearsal-based continual learning achieves a top-5 classification accuracy close to the upper bound, while simultaneously exhibiting a runtime close to the lower bound.

关键词： Training Continuing education Deep learning Accuracy Runtime Upper bound Scalability Training data Graphics processing units Supercomputers

来源：评论

学校读者我要写书评

暂无评论

Training Computer Scientists for the Challenges of Hybrid Quantum-Classical computing

Training Computer Scientists for the Challenges of Hybrid Qu...

引用

IEEE/ACM International symposium on Cluster computing and the Grid (CCGRID)

作者： Vincenzo De Maio Meerzhan Kanatbekova Felix Zilk Nicolai Friis Tobias Guggemos Ivona Brandic HPC Laboratory Institute of Information Systems Engineering TU Wien Vienna Austria Atominstitut TU Wien Vienna Austria Faculty of Physics Vienna Center for Quantum Science and Technology (VCQ) University of Vienna Vienna Austria Christian Doppler Laboratory for Photonic Quantum Computer Faculty of Physics University of Vienna Vienna Austria

ISBN: (数字)9798350395662

ISBN: (纸本)9798350395679

As we enter the post-Moore era, we experience the rise of various non-von-Neumann-architectures to address the increasing computational demand for modern applications, with quantum computing being among the most prominent and promising technologies. However, this development creates a gap in current computer science curricula since most quantum computing lectures are strongly physics-oriented and have little intersection with the remaining curriculum of computer science. this fact makes designing an appealing course very difficult, in particular for non-physicists. Furthermore, in the academic community, there is consensus that quantum computers are going to be used only for specific computational tasks (e.g., in computational science), where hybrid systems - combined classical and quantum computers - facilitate the execution of an application on both quantum and classical computing resources. A hybrid system thus executes only certain suitable parts of an application on the quantum machine, while other parts are executed on the classical components of the system. To fully exploit the capabilities of hybrid systems and to meet future requirements in this emerging field, we need to prepare a new generation of computer scientists with skills in both distributed computing and quantum computing. To bridge this existing gap in standard computer science curricula, we designed a new lecture and exercise series on Hybrid Quantum-Classical Systems, where students learn how to decompose applications and implement computational tasks on a hybrid quantum-classical computational continuum. While learning the inherent concepts underlying quantum systems, students are obligated to apply techniques and methods they are already familiar with, making the entrance to the field of quantum computing comprehensive yet appealing and accessible to students of computer science.

关键词： Computer science Training Bridges Quantum system Cloud computing Quantum computing Scientific computing Hybrid power systems Standards

来源：评论

学校读者我要写书评

暂无评论

Evasion attacks on ML in domains with nonlinear constraints

Evasion attacks on ML in domains with nonlinear constraints

引用

Cluster, Cloud and Internet computing Workshops (CCGridW), IEEE/ACM International symposium on

作者： Mateusz Krzysztoń Bartosz Bok Paweł Żakieta Joanna Kołodziej Department of Distributed Systems Research and Academic Computer Network (NASK-PIB) Warsaw Poland Department of Computer Sciences Cracow University of Technology Cracow Poland

ISBN: (数字)9798350377514

ISBN: (纸本)9798350377521

Cybersecurity efforts aim to protect computer systems, especially complex systems with dynamically changing architectures like mobile computational clouds, from digital attacks. the use of machine learning (ML) models in these systems to analyze and process data, allocate resources or monitor and manage infrastructure is increasingly the field of hackers and the target of sophisticated and increasingly difficult-todetect attacks. Adversarial machine learning (AML) is a class of techniques and methods that attempt to "fool" classical ML algorithms by using, among others, deceptive data or modifying the parameters of cyber-physical systems (CPS).this paper presents a new generic evasion attack model for generating targeted attacks on the ML binary classifiers in domains with nonlinear constraints. We used GD (Gradient Descent) and Adam (Adaptive Moment Estimation) optimization algorithms as the most important internal components of two variants of our attack model. Such a model was then evaluated in an experimental analysis. the achieved results show that the new generic evasion attack model effectively generates targeted attacks on ML binary classifiers, utilizing GD and Adam optimization algorithms. this model was evaluated through experimental analysis, demonstrating its potential in cybersecurity contexts. through this approach, the research contributes significantly to the field of adversarial machine learning by presenting a novel method that challenges the robustness of ML models under specific nonlinear constraints.

关键词： Analytical models Adaptation models Machine learning algorithms Mathematical models Data models Adversarial machine learning Robustness Classification algorithms Optimization Monitoring

来源：评论

学校读者我要写书评

暂无评论

TianheStar: Orchestrating SSSP Applications on Tianhe Supercomputer

TianheStar: Orchestrating SSSP Applications on Tianhe Superc...

引用

IEEE/ACM International symposium on Cluster computing and the Grid (CCGRID)

作者： Xinbiao Gan Qian Tang Feng Xiong Shijie Li Bo Yang Tiejun Li School of Computer National University of Defense Technology

ISBN: (数字)9798350395662

ISBN: (纸本)9798350395679

computing single-source shortest paths (SSSP) is one of the fundamental problems in graph theory and is also essential for data-intensive applications. As the potential of artificial intelligence (AI) continues to be explored, and with the advent of exascale supercomputing, there is a growing need for an extremely fast graph engine for SSSP applications. Current distributed SSSP engines for large-scale graph applications, unfortunately, often exhibit poor efficiency when running on supercomputers. In this paper, we introduce TianheStar, an ultra-fast SSSP engine designed specifically for graph search on the Tianhe supercomputer. TianheStar effectively minimizes communication costs and establishes a new balance between computation and communication. the key idea of TianheStar is to leverage network topology information for performing topology-aware message aggregation and architecture-aware group communication. these two techniques effectively reduce the number of messages and the average number of communication hops, respectively. We validate TianheStar using Graph500, a widely adopted benchmark for graph search on supercomputers. Extensive evaluation demonstrates that, compared to the state-of-the-art solutions, TianheStar achieves a remarkable performance improvement. We have deployed TianheStar on the latest Tianhe supercomputer and secured the top position in the latest Graph500. We achieved an outstanding performance of 23,021 GTEPS (Giga Traversed Edges Per Second) for SSSP using 4096 nodes. Furthermore, we have delved into real-world graphs representing the USA road networks and conducted computations to determine the shortest paths between vertices. Our experimental results demonstrate that TianheStar can traverse the USA road network, comprising over 58,333,344 edges, in less than 0.1 second on the Tianhe supercomputer. this performance represents a speedup of over a thousand times compared to parallel shortest-path graph computations on the Aziz supercompu

关键词： Cloud computing Costs Network topology Roads High performance computing Benchmark testing Supercomputers Graph theory Artificial intelligence Engines

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Solution to Provide End-to-End Flow Control and Congestion Management in High-Performance Interconnection Networks

A Hybrid Solution to Provide End-to-End Flow Control and Con...

引用

IEEE/ACM International symposium on Cluster computing and the Grid (CCGRID)

作者： Alberto Merino Jesus Escudero-Sahuquillo Pedro Javier Garcia Francisco J. Quiles Fei Chen Yunping Lyu Long Yan Jose Duato Computing Systems Department Universidad de Castilla-La Mancha Spain Huawei Technologies Co. Ltd. Shenzhen China Royal Spanish Academy of Sciences Spain

ISBN: (数字)9798350395662

ISBN: (纸本)9798350395679

Congestion seriously threatens high-performance interconnection networks in supercomputers and data centers, where thousands of server nodes generate massive communication operations when running highly parallel and distributed applications and services. In recent years, numerous solutions have been proposed to address congestion and its effects, including flow control (e.g., priority flow control, PFC) to prevent packet dropping at congested buffers, injection throttling to detect congested points and notify source server nodes to reduce the injection rate of congesting flows, and congestion isolation (as defined in the IEEE 802.1Qcz standard) that stores the congesting flows in separate queues or virtual channels (VCs) at switch buffers. Unfortunately, these solutions have exhibited important drawbacks, such as the prohibitive latency generated by flow control during congestion situations, the slow and ineffective response of injection throttling, or the excessive resources required to identify and isolate congesting flows. In this paper, we propose a hybrid congestion management solution, called 3SC (from three strategies combined), which combines end-to-end flow control, injection throttling, and congesting-flow isolation. 3SC significantly reduces Head-of-Line (HoL) blocking by isolating congesting flows in special queues at some switches, swiftly throttles the injection of these congesting flows, and significantly decreases the number of flow control messages compared to PFC. To evaluate our proposal, we have conducted a large set of simulation experiments for different network configurations and realistic traffic patterns. the results demonstrate that 3SC is efficient and feasible, making it a promising solution for future interconnection network designs.

关键词： Degradation Data centers Cloud computing Multiprocessor interconnection Switches Traffic control Supercomputers Servers Proposals Standards

来源：评论

学校读者我要写书评

暂无评论

Digital Twins at the Edge to Track Mobility for MaaS Applications 24

Digital Twins at the Edge to Track Mobility for MaaS Applica...

引用

IEEE/ACM 24th International symposium on distributed Simulation and Real Time Applications (DS-RT)

作者： Campolo, Claudia Genovese, Giacomo Molinaro, Antonella Pizzimenti, Bruno Univ Mediterranea Reggio Calabria Calabria Italy

ISBN: (纸本)9781728173436

the research into wireless communication and mobile computing is called to formulate novel smart mobility solutions to improve the quality of a citizen's life in smart cities. In such a context, in this paper we elaborate on the role of technologies like multi-access edge computing (MEC), Internet of things (IoT) messaging protocols, such as Constrained Application Protocol (CoAP) and Message Queue Telemetry Transport (MQTT), and virtualization (i.e., digital twins) in the design of a framework enabling the collection and processing of data about the mobility of commuters and public transport vehicles. Such data have the purpose to feed mobility monitoring and transport planning solutions. A Proof-of-Concept (PoC) is developed to validate the framework under realistic experimental settings. Results in terms of efficiency and effectiveness of the considered messaging protocols are reported.

关键词： Multi-access Edge computing CoAP Digital Twin OMA LwM2M MQTT MaaS

来源：评论

学校读者我要写书评

暂无评论

Collision Avoidance Proposal in a MEC based VANET environment 24

Collision Avoidance Proposal in a MEC based VANET environmen...

引用

IEEE/ACM 24th International symposium on distributed Simulation and Real Time Applications (DS-RT)

作者： Nevigato, Nicolas Tropea, Mauro De Rango, Floriano Univ Calabria Dimes Dept Arcavacata Di Rende Italy

ISBN: (纸本)9781728173436

Mobile Edge computing (MEC) is a new network paradigm that allows resource management and IT services at the edge of a communication network and, so, closer to the devices guaranteeing low latency and high bandwidth requirements. this characteristic makes MEC paradigm suitable for critical communication services used in collaboration with container-based virtualization and with 5G networks. In this paper, an implementation of a collision avoidance system based on MEC in a VANET environment is proposed. this system makes use of cloud and edge computing and it is able to switch communication from edge to cloud server and vice versa when possible, trying to guarantee the required constraints and balancing the communication among the servers avoiding of overloading edge layer. the simulation results have proved how, in some cases, the MEC-5G combination is the best solution for avoiding collisions in a VANET environment.

关键词： VANET Collision Avoidance Mobile Edge computing (MEC) 5G

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共34页 << < 3 4 5 6 7 8 9 10 11 12 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：