检索结果-内蒙古大学图书馆

A prompt-based approach to adversarial example generation and robustness enhancement

Frontiers of Computer Science 2024年第4期18卷 85-96页

作者： Yuting YANG Pei HUANG Juan CAO Jintao LI Yun LIN Feifei MA Key Lab of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing 100190China School of Computer Science and Technology University of Chinese Academy of SciencesBeijing 100049China Department of Computer Science Stanford UniversityCA 94305USA School of Computing National University of SingaporeSingapore 119077Singapore Laboratory of Parallel Software and Computational Science Institute of SoftwareChinese Academy of SciencesBeijing 100190China

Recent years have seen the wide application of natural language processing(NLP)models in crucial areas such as finance,medical treatment,and news media,raising concerns about the model robustness and *** find that prompt paradigm can probe special robust defects of pre-trained language *** prompt texts are first constructed for inputs and a pre-trained language model can generate adversarial examples for victim models via *** results show that prompt paradigm can efficiently generate more diverse adversarial examples besides synonym ***,we propose a novel robust training approach based on prompt paradigm which incorporates prompt texts as the alternatives to adversarial examples and enhances robustness under a lightweight minimax-style optimization *** on three real-world tasks and two deep neural models show that our approach can significantly improve the robustness of models to resist adversarial attacks.

关键词： robustness adversarial example prompt learning pre-trained language model

来源：评论

学校读者我要写书评

暂无评论

A Fast Scalable Hardware Priority Queue and Optimizations for Multi-Pushes

A Fast Scalable Hardware Priority Queue and Optimizations fo...

引用

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

作者： Samuel Collinson Allan Bai Oliver Sinnen Department of Electrical Computer and Software Engineering Parallel and Reconfigurable Computing Lab University of Auckland New Zealand

ISBN: (数字)9798350364606

ISBN: (纸本)9798350364613

Priority queues (PQ) are an essential data structure for many important algorithms. Hardware implementations of priority queues can accelerate such algorithms significantly. Usually a choice has to be made between very fast (fixed-size) hardware PQs or scalable PQs. Fast hardware queues can provide single cycle push and pop operations, but are limited in size. Scalable hardware queues use embedded memory to achieve scalability, but thereby compromise on speed. This paper proposes a fast and scalable hardware priority queue that can be used for general purpose. It is based on a modular and flexible hybrid design, using a shift register queue combined with a heap-based queue. In the best case, i.e. when only the first queue is needed, push and pop operations only take a single cycle. In an experimental evaluation on a Xilinx FPGA we demonstrate that performance of the hybrid queue maintains a good balance between performance and scalability even for applications where the size of the working set of data can have large variance. We further propose an optimisation of the heap-based queue to support workloads that repeat several consecutive push operations followed by a single pop operation, which is the workload, for instance, in state space search or ray-tracing.

关键词： Distributed processing Scalability Sociology Ray tracing Shift registers Data structures Hardware

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

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

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

引用

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

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

关键词：

来源：评论

学校读者我要写书评

暂无评论

GraphBLAS: C++ Iterators for Sparse Matrices 36

GraphBLAS: C++ Iterators for Sparse Matrices

引用

36th IEEE International parallel and Distributed Processing Symposium Workshops, IPDPSW 2022

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

ISBN: (纸本)9781665497473

Iteration over opaque, generic data structures is an important feature of many C++ libraries. Aggressive compiler optimization and inlining enables generic C++ iterators to iterate over complex data structures with performance comparable to that of hand-tuned code with C-language (raw) pointers. In this paper, we describe the sparse matrix iterators in the current draft of the C++ GraphBLAS API, their support for a variety of backend data formats, and implementation strategies we have considered. We compare performance of these iterators to that of hand-tuned iteration with raw pointers, showing that our iterators introduce minimal overhead. We consider extensions to our iterator design for interoperability with the draft C++ Graph Library proposal and to support different semantics for iterating over sparse matrices (by row, by column, by specific diagonals, etc.). © 2022 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Strong consistency is not hard to get: Twophase locking and twophase commit on thousands of cores 46th

Strong consistency is not hard to get: Twophase locking and ...

引用

46th International Conference on Very Large Data Bases, VLDB 2020

作者： Barthels, Claude Müller, Ingo Taranov, Konstantin Alonso, Gustavo Hoefler, Torsten Systems Group Department of Computer Science ETH Zurich Switzerland Scalable Parallel Computing Lab Department of Computer Science ETH Zurich Switzerland

Concurrency control is a cornerstone of distributed database engines and storage systems. In pursuit of scalability, a common assumption is that Two-Phase Locking (2PL) and Two-Phase Commit (2PC) are not viable solutions due to their communication overhead. Recent results, however, have hinted that 2PL and 2PC might not have such a bad performance. Nevertheless, there has been no attempt to actually measure how a state-of-the-art implementation of 2PL and 2PC would perform on modern hardware. The goal of this paper is to establish a baseline for concurrency control mechanisms on thousands of cores connected through a lowlatency network. We develop a distributed lock table supporting all the standard locking modes used in database engines. We focus on strong consistency in the form of strict serializability implemented through strict 2PL, but also explore read-committed and repeatableread, two common isolation levels used in many *** do not leverage any known optimizations in the locking or commit parts of the protocols. The surprising result is that, for TPC-C, 2PL and 2PC can be made to scale to thousands of cores and hundreds of machines, reaching a throughput of over 21 million transactions per second with 9.5 million New Order operations per second. Since most existing relational database engines use some form of locking for implementing concurrency control, our findings provide a path for such systems to scale without having to significantly redesign transaction management. To achieve these results, our implementation relies on Remote Direct Memory Access (RDMA). Today, this technology is commonly available on both Infiniband as well as Ethernet networks, making the results valid across a wide range of systems and platforms, including database appliances, data centers, and cloud environments. © VLDB Endowment.

关键词： Concurrency control

来源：评论

学校读者我要写书评

暂无评论

Resource-Aware Multi-Criteria Vehicle Participation for Federated Learning in Internet of Vehicles

SSRN

引用

SSRN 2023年

作者： Wen, Jie Zhang, Jingbo Zhang, Zhixia Cui, Zhihua Cai, Xingjuan Chen, Jinjun The Shanxi Key Laboratory of Advanced Control and Equipment intelligence Taiyuan University of Science and Technology Shanxi Taiyuan China The Shanxi Key Laboratory of Big Data Analysis and Parallel Computing Taiyuan University of Science and Technology Shanxi Taiyuan China The State Key Lab for Novel Software Technology Nanjing University China Department of Computing Technologies Swinburne University of Technology Melbourne Australia

Federated learning (FL), as a safe distributed training mode, provides strong support for the edge intelligence of the Internet of Vehicles (IoV) to realize efficient collaborative control and safe data sharing. However, due to the resource limitation and the instability of training environment in the complex IoV, ideal performance of FL cannot be achieved. Since considering the actual resource constraints and federated task requirements, the diversified device selection criteria make the resource-aware vehicle selection problem become a multi-criteria selection problem. To effectively support FL for IoV, the resource-aware multi-criteria vehicle selection problem was described as a many-objective optimization problem, and proposed a resource-aware many-objective vehicle selection model (RA-MaOVSM) to optimize resource efficiency. The RA-MaOVSM considering heterogeneous resources (like computation resources, communication resources, energy resources and data resources) of on-board devices in IoV, and realizes the joint optimization of learning efficiency, energy cost and global performance. Additionally, a novel probability distribution combination game strategy is applied to many-objective evolutionary algorithm (MaOEA) for improving the model solving performance. Simulation results demonstrate that RA-MaOVSM can effectively optimize the IoV resources and FL model performance, and the designed algorithm exhibits good convergence and distribution, achieving a good balance among multiple device selection criteria. © 2023, The Authors. All rights reserved.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

GraphBLAS: C++ Iterators for Sparse Matrices

GraphBLAS: C++ Iterators for Sparse Matrices

引用

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

作者： Benjamin Brock Scott McMillan Aydı n Buluç Timothy G. Mattson José E. Moreira EECS Department University of California Berkeley CA Software Engineering Institute Carnegie Mellon University Pittsburgh PA Computational Research Department Lawrence Berkeley National Laboratory Berkeley CA Parallel Computing Lab Intel Ocean Park WA IBM Thomas J. Watson Research Center Yorktown Heights NY

ISBN: (数字)9781665497473

ISBN: (纸本)9781665497480

关键词： Distributed processing Conferences Semantics C++ languages Data structures Libraries Sparse matrices

来源：评论

学校读者我要写书评

暂无评论

Inferring coupling strengths of mixed-mode oscillations in red-giant stars using deep learning

arXiv

引用

arXiv 2023年

作者： Dhanpal, Siddharth Benomar, Othman Hanasoge, Shravan Takata, Masao Panda, Subrata Kundu, Abhisek Department of Astronomy and Astrophysics Tata Institute of Fundamental Research Mumbai400005 India Center for Space Science NYUAD Institute New York University Abu Dhabi PO Box 129188 Abu Dhabi United Arab Emirates Division of Solar and Plasma Astrophysics NAOJ Mitaka Tokyo Japan Department of Astronomy School of Science The University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo113-0033 Japan Parallel Computing Lab Intel Labs Bangalore India

Asteroseismology is a powerful tool that may be applied to shed light on stellar interiors and stellar evolution. Mixed modes, behaving as acoustic waves in the envelope and buoyancy modes in the core, are remarkable because they allow for probing the radiative cores and evanescent zones of red-giant stars. Here, we have developed a neural network that can accurately infer the coupling strength, a parameter related to the size of the evanescent zone, of solar-like stars in ∼5 milliseconds. In comparison with existing methods, we found that only ∼43% inferences were in agreement to within a difference of 0.03 on a sample of ∼1,700 Kepler red giants. To understand the origin of these differences, we analyzed a few of these stars using independent techniques such as the Monte Carlo Markov Chain method and Echelle diagrams. Through our analysis, we discovered that these alternate techniques are supportive of the neural-net inferences. We also demonstrate that the network can be used to yield estimates of coupling strength and period spacing in stars with structural discontinuities. Our findings suggest that the rate of decline in the coupling strength in the red-giant branch is greater than previously believed. These results are in closer agreement with calculations of stellar-evolution models than prior estimates, further underscoring the remarkable success of stellar-evolution theory and computation. Additionally, we show that the uncertainty in measuring period-spacing increases rapidly with diminishing coupling strength. © 2023, CC BY-NC-ND.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

dMazeRunner: Optimizing Convolutions on Dataflow Accelerators

dMazeRunner: Optimizing Convolutions on Dataflow Accelerator...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Shail Dave Aviral Shrivastava Youngbin Kim Sasikanth Avancha Kyoungwoo Lee Compiler Microarchitecture Lab Arizona State University Department of Computer Science Yonsei University Parallel Computing Lab Intel Labs

ISBN: (数字)9781509066315

ISBN: (纸本)9781509066322

Convolution neural networks (CNNs) can be efficiently executed on dataflow accelerators. However, the vast space of executing convolutions on computational and memory resources of accelerators makes difficult for programmers to automatically and efficiently accelerate the convolutions and for architects to achieve efficient accelerator designs. We propose dMazeRunner framework, which allows users to optimize execution methods for accelerating convolution and matrix multiplication on a given architecture and to explore dataflow accelerator designs for efficiently executing CNN models. dMazeRunner determines efficient dataflows tailored for CNN layers and achieves efficient execution methods for CNN models within several seconds.

关键词：

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：