检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Gao, Fei Hu, Ming Xie, Zhiyu Shi, Peichang Xie, Xiaofei Yi, Guodong Wang, Huaimin National Key Lab. of Parallel and Distributed Processing National University of Defense Technology Changsha China School of Computing and Information Systems Singapore Management University Singapore Xiangjiang Lab Changsha China

With advancements in AI infrastructure and Trusted Execution Environment (TEE) technology, Federated Learning as a Service (FLaaS) through JointCloud computing (JCC) is promising to break through the resource constraints caused by heterogeneous edge devices in the traditional Federated Learning (FL) paradigm. Specifically, with the protection from TEE, data owners can achieve efficient model training with high-performance AI services in the cloud. By providing additional FL services, cloud service providers can achieve collaborative learning among data owners. However, FLaaS still faces three challenges, i.e., i) low training performance caused by heterogeneous data among data owners, ii) high communication overhead among different clouds (i.e., data centers), and iii) lack of efficient resource scheduling strategies to balance training time and cost. To address these challenges, this paper presents a novel asynchronous FL approach named NebulaFL for collaborative model training among multiple clouds. To address data heterogeneity issues, NebulaFL adopts a version control-based asynchronous FL training scheme in each data center to balance training time among data owners. To reduce communication overhead, NebulaFL adopts a decentralized model rotation mechanism to achieve effective knowledge sharing among data centers. To balance training time and cost, NebulaFL integrates a reward-guided strategy for data owners selection and resource scheduling. The experimental results demonstrate that, compared to the state-of-the-art FL methods, NebulaFL can achieve up to 5.71% accuracy improvement. In addition, NebulaFL can reduce up to 50% communication overhead and 61.94% costs under a target accuracy. Copyright © 2024, The Authors. All rights reserved.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Fuzzy correlational analysis for dynamic consolidation of virtual machines in cloud computing environment

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2023年第PartD期126卷

作者： Bertei, Alex Foss, Luciana Bedregal, Benjamin Reiser, Renata Univ Fed Pelotas Lab Ubiquitous & Parallel Syst Pelotas RS Brazil Fed Univ Rio Grande de Norte Dept Informat & Appl Math Postgrad Program Syst & Computing Natal RN Brazil

This theoretical research in fuzzy correlation analysis integrates data uncertainty analysis by measuring the strength of the linear relationship restricted to two fuzzy sets. As the relevant contribution to this research area, this paper presents the axiomatic definition of the n-dimensional generalized fuzzy correlation coefficient (nGCC), assigning to n input fuzzy sets an output value in the interval [-1,1]. Thus, the properties of general overlap functions and fuzzy negations are studied, discussing binary non-normed restricted dissimilarity functions, and the n-dimensional non-normed conjunctive functions. This study provides new methods for the n-dimensional generalized fuzzy correlation coefficient analysis, regarding their applications in solving multi-criteria and decision-making problems founded on fuzzy logic extensions. The n-dimensional non-normed conjunctive aggregation functions are also introduced, as range domain extensions from [0,1] to [-1.1], covering the interpretation of negative to positive variable associations. The proposal correlation analysis promotes a better evaluation and data selection even when more than one algorithm is applied to evaluate the reduction methods in the defuzzification process based on Interval-valued Fuzzy Logic. We also investigate the relevance to determine a reliable result from the fuzzy inference system based on the nGCC methodology. This correlation methodology applied to the Interval Fuzzy Load Balancing for Cloud computing (Int-FLBCC) model contributes as a flexible approach for virtual machines dynamic consolidation enabling improvements in resource usage and power efficiency, improving the computational system's energy efficiency. So, the nGCC methodology extends the Int-FLBCC model by adding other degrees of reliability to the results obtained with diverse evaluations through n-dimensional generalized fuzzy correlation coefficient expressions, exploring average aggregations as arithmetic and exponential me

关键词： Pearsen's correlation coefficient Cloud computing Fuzzy set n-dimensional fuzzy correlation analysis Multi-criteria Decision-making Interval-valued fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

C++ and Interoperability between Libraries: The GraphBLAS C++ Specification

C++ and Interoperability between Libraries: The GraphBLAS C+...

引用

2023 IEEE International parallel and Distributed Processing Symposium Workshops, IPDPSW 2023

作者： Brock, Benjamin McMillan, Scott Buluc, Aydin Mattson, Timothy G. Moreira, Jose E. Parallel Computing Lab Intel United States Software Engineering Institute Carnegie Mellon University United States Lawrence Berkeley National Laboratory Computational Research Department United States University of California EECS Department Berkeley United States IBM Thomas J. Watson Research Center United States

ISBN: (纸本)9798350311990

Interoperability between libraries is often hindered by incompatible data formats, which can necessitate creating new copies of data when transferring data back and forth between different libraries. This additional data movement incurs additional runtime costs, particularly for sparse applications, where the costs of data movement often dwarf compute costs. In this paper, we investigate interoperability in the context of the C++ GraphBLAS Specification, where C++ concepts allow GraphBLAS algorithms to accept any matrix type as long as it follows the matrix interface defined in the GraphBLAS matrix concept. We first develop non-owning, lazily evaluated adapted views for a number of external data structures, including two categories of graphs defined in the Northwest Graph Library (NWGraph) and traditional pointer-based CSR data structures. These adapted views fulfill the C++ GraphBLAS matrix concept, allowing them to be used inside GraphBLAS algorithms. We then evaluate the performance of these adapted views across two kernels, matrix reduction and sparse times dense matrix multiplication (SpMM), where the performance achieved using a single generic implementation with these views largely matches the performance achieved operating directly on the original data structures, with a slight performance loss in one case. We then propose a mechanism for automatically discovering the availability of these views, allowing algorithms to directly accept external data structures. We also discuss potential extensions to the C++ GraphBLAS specification that might eliminate the small performance dip observed for one of the views. © 2023 IEEE.

关键词： Data structures

来源：评论

学校读者我要写书评

暂无评论

Towards a GraphBLAS Implementation for Go

Towards a GraphBLAS Implementation for Go

引用

IEEE International Symposium on parallel and Distributed Processing Workshops and Phd Forum (IPDPSW)

作者： Pascal Costanza Ibrahim Hurt Timothy G. Mattson Intel Extreme Scale Computing Group Brussels Belgium Intel Extreme Scale Computing Group Hillsboro OR USA Intel Parallel Computing Lab Ocean Park WA USA

ISBN: (数字)9781665497473

ISBN: (纸本)9781665497480

The GraphBLAS are building blocks for constructing graph algorithms as linear algebra. They are defined mathematically with the goal that they would eventually map onto a variety of programming languages. Today they exist in C, C++, Python, MATlab®, and Julia. In this paper, we describe the GraphBLAS for the Go programming language. A particularly interesting aspect of this work is that using the concurrency features of the Go language, we aim to build a runtime system that uses the GraphBLAS nonblocking mode by default.

关键词： Concurrent computing Distributed processing Runtime Conferences Prototypes Linear algebra Licenses

来源：评论

学校读者我要写书评

暂无评论

PRACTICAL MASSIVELY parallel MONTE-CARLO TREE SEARCH APPLIED TO MOLECULAR DESIGN 9

PRACTICAL MASSIVELY PARALLEL MONTE-CARLO TREE SEARCH APPLIED...

引用

9th International Conference on Learning Representations, ICLR 2021

作者： Yang, Xiufeng Aasawat, Tanuj Kr Yoshizoe, Kazuki Chugai Pharmaceutical Co. Ltd Japan Parallel Computing Lab - India Intel Labs India RIKEN Center for Advanced Intelligence Project Japan

It is common practice to use large computational resources to train neural networks, known from many examples, such as reinforcement learning applications. However, while massively parallel computing is often used for training models, it is rarely used to search solutions for combinatorial optimization problems. This paper proposes a novel massively parallel Monte-Carlo Tree Search (MP-MCTS) algorithm that works efficiently for a 1,000 worker scale on a distributed memory environment using multiple compute nodes and applies it to molecular design. This paper is the first work that applies distributed MCTS to a real-world and non-game problem. Existing works on large-scale parallel MCTS show efficient scalability in terms of the number of rollouts up to 100 workers. Still, they suffer from the degradation in the quality of the solutions. MP-MCTS maintains the search quality at a larger scale. By running MP-MCTS on 256 CPU cores for only 10 minutes, we obtained candidate molecules with similar scores to non-parallel MCTS running for 42 hours. Moreover, our results based on parallel MCTS (combined with a simple RNN model) significantly outperform existing state-of-the-art work. Our method is generic and is expected to speed up other applications of MCTS. © 2021 ICLR 2021 - 9th International Conference on Learning Representations. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

PDB-Struct: A Comprehensive Benchmark for Structure-based Protein Design

arXiv

引用

arXiv 2023年

作者： Wang, Chuanrui Zhong, Bozitao Zhang, Zuobai Chaudhary, Narendra Misra, Sanchit Tang, Jian Mila - Québec AI Institute Canada Université de Montréal Canada Intel Parallel Computing Lab HEC Montréal Canada CIFAR AI Chair Canada

Structure-based protein design has attracted increasing interest, with numerous methods being introduced in recent years. However, a universally accepted method for evaluation has not been established, since the wet-lab validation can be overly time-consuming for the development of new algorithms, and the in silico validation with recovery and perplexity metrics is efficient but may not precisely reflect true foldability. To address this gap, we introduce two novel metrics: refoldability-based metric, which leverages high-accuracy protein structure prediction models as a proxy for wet lab experiments, and stability-based metric, which assesses whether models can assign high likelihoods to experimentally stable proteins. We curate datasets from high-quality CATH protein data, high-throughput de novo designed proteins, and mega-scale experimental mutagenesis experiments, and in doing so, present the PDB-Struct benchmark that evaluates both recent and previously uncompared protein design methods. Experimental results indicate that ByProt, ProteinMPNN, and ESM-IF perform exceptionally well on our benchmark, while ESM-Design and AF-Design fall short on the refoldability metric. We also show that while some methods exhibit high sequence recovery, they do not perform as well on our new benchmark. Our proposed benchmark paves the way for a fair and comprehensive evaluation of protein design methods in the future. Code is available at https://***/WANG-CR/PDB-Struct. Copyright © 2023, The Authors. All rights reserved.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

Introducing the Quantum Research Kernels: Lessons from Classical parallel computing

arXiv

引用

arXiv 2022年

作者： Matsuura, A.Y. Mattson, Timothy G. Applications and Quantum Architecture Lab Intel Corp HillsboroOR United States Parallel Computing Lab Intel Corp. IlwacoWA United States

Quantum computing represents a paradigm shift for computation requiring an entirely new computer architecture. However, there is much that can be learned from traditional classical computer engineering. In this paper, we describe the parallel Research Kernels (PRK), a tool that was very useful for designing classical parallel computing systems. The PRK are simple kernels written to expose bottlenecks that limit classical parallel computing performance. We hypothesize that an analogous tool for quantum computing, Quantum Research Kernels (QRK), may similarly aid the codesign of software and hardware for quantum computing systems, and we give a few examples of representative QRKs. Copyright © 2022, The Authors. All rights reserved.

关键词： Hardware-software codesign

来源：评论

学校读者我要写书评

暂无评论

A Guaranteed Approximation Algorithm for Scheduling Fork-Joins with Communication Delay

A Guaranteed Approximation Algorithm for Scheduling Fork-Joi...

引用

International Symposium on parallel and Distributed Processing (IPDPS)

作者： Pierre-François Dutot Yeu-Shin Fu Nikhil Prasad Oliver Sinnen CNRS Inria Grenoble INP* LIG Univ. Grenoble Alpes Grenoble France Dept. of Electrical Computer & Software Engineering Parallel and Reconfigurable Computing Lab University of Auckland Auckland New Zealand

Scheduling task graphs with communication delay is a widely studied NP-hard problem. Many heuristics have been proposed, but there is no constant approximation algorithm for this classic model. In this paper, we focus on the scheduling of the important class of fork-join task graphs (describing many types of common computations) on homogeneous processors. For this sub-case, we propose a guaranteed algorithm with a $\left( {1 + \frac{m}{{m - 1}}} \right)$-approximation factor, where m is the number of processors. The algorithm is not only the first constant approximation for an important sub-domain of the classic scheduling problem, it is also a practical algorithm that can obtain shorter makespans than known heuristics. To demonstrate this, we propose adaptations of known scheduling heuristic for the specific fork-join structure. In an extensive evaluation, we then implemented these algorithms and scheduled many fork-join graphs with up to thousands of tasks and various computation time distributions on up to hundreds of processors. Comparing the obtained results demonstrates the competitive nature of the proposed approximation algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On Achieving Privacy-Preserving State-of-the-Art Edge Intelligence

arXiv

引用

arXiv 2023年

作者： Chabal, Daphnee Sapra, Dolly Mann, Zoltán Ádám Complex Cyber Infrastructure group University of Amsterdam Lab42 Science Park 900 Amsterdam1012 WX Netherlands Parallel Computing Systems group University of Amsterdam Lab42 Science Park 900 Amsterdam1012 WX Netherlands

Deep Neural Network (DNN) Inference in Edge computing, often called Edge Intelligence, requires solutions to insure that sensitive data confidentiality and intellectual property are not revealed in the process. Privacy-preserving Edge Intelligence is only emerging, despite the growing prevalence of Edge computing as a context of Machine-Learning-as-a-Service. Solutions are yet to be applied, and possibly adapted, to state-of-the-art DNNs. This position paper provides an original assessment of the compatibility of existing techniques for privacy-preserving DNN Inference with the characteristics of an Edge computing setup, highlighting the appropriateness of secret sharing in this context. We then address the future role of model compression methods in the research towards secret sharing on DNNs with state-of-the-art performance. © 2023, CC BY-NC-SA.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficient Detection Of SQL Injection Attack(SQLIA) Using Pattern-based Neural Network Model

Efficient Detection Of SQL Injection Attack(SQLIA) Using Pat...

引用

International Conference on computing, Communication, and Intelligent Systems (ICCCIS)

作者： Meharaj Begum A Michael Arock Bio-informatics and Parallel Computing Lab National Institute of Technology Trichy Tamilnadu India

ISBN: (数字)9781728185293

ISBN: (纸本)9781728185309

Web application vulnerability is one of the major causes of cyber attacks. Cyber criminals exploit these vulnerabilities to inject malicious commands to the unsanitized user input in order to bypass authentication of the database through some cyber-attack techniques like cross site scripting (XSS), phishing, Structured Query Language Injection Attack (SQLIA), malware etc., Although many research works have been conducted to resolve the above mentioned attacks, only few challenges with respect to SQLIA could be resolved. Ensuring security against complete set of malicious payloads are extremely complicated and demanding. It requires appropriate classification of legitimate and injected SQL commands. The existing approaches dealt with limited set of signatures, keywords and symbols of SQL queries to identify the injected queries. This work focuses on extracting SQL injection patterns with the help of existing parsing and tagging techniques. Pattern-based tags are trained and modeled using Multi-layer Perceptron which significantly performs well in classification of queries with accuracy of 94.4% which is better than the existing approaches.

关键词： Structured Query Language Computational modeling Phishing SQL injection Tagging Security Payloads

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

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

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：