检索结果-内蒙古大学图书馆

Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence

作者： Hao Wang Dawei Feng Bo Ding Wei Li College of Computer National University of Defense Technology China National Laboratory for Parallel and Distributed Processing National University of Defense Technology China Independent Researcher China

ISBN: (纸本)9781450398336

Offline imitative learning(OIL) is often used to solve complex continuous decision-making tasks. For these tasks such as robot control, automatic driving and etc., it is either difficult to design an effective reward for learning or very expensive and time-consuming for agents to collect data interactively with the environment. However, the data used in previous OIL methods are all gathered by reinforcement learning algorithms guided by task-specific rewards, which is not a true reward-free premise and still suffers from the problem of designing an effective reward function in real tasks. To this end, we propose the reward-free exploratory data driven offline imitation learning (ExDOIL) framework. ExDOIL first trains an unsupervised reinforcement learning agent by interacting with the environment, and collects enough unsupervised exploration data during training; Then, a task independent yet simple and efficient reward function is used to relabel the collected data; Finally, an agent is trained to imitate the expert to complete the task through a conventional RL algorithm such as TD3. Extensive experiments on continuous control tasks demonstrate that the proposed framework can achieve better imitation performance(28% higher episode returns on average) comparing with previous SOTA method(ORIL) without any task-specific rewards.

关键词： dataset

来源：评论

学校读者我要写书评

暂无评论

Sparse Matrix Reordering Method Selection with parallel Computing and Deep Learning

Sparse Matrix Reordering Method Selection with Parallel Comp...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Rui Xia Jihu Guo Huajian Zhang Shun Yang Qinglin Wang Jie Liu College of Computer Science and Techonology National University of Defense Technology Changsha China Laboratory of Digitizing Software for Frontier Equipment National University of Defense Technology Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Sparse matrix reordering is an important step in Cholesky decomposition. By reordering the rows and columns of the matrix, the time of computation and storage cost can be greatly reduced. With the proposal of various reordering algorithms, the selection of suitable reordering methods for various matrices has become an important research topic. In this paper, we propose a method to predict the optimal reordering method by visualizing sparse matrices in chunks in a parallel manner and feeding them into a deep convolutional neural network. The results show that the theoretical performance can reach 95% of the optimal performance, the prediction accuracy of the method can reach up to 85%, the parallel framework achieves an average speedup ratio of 11.35 times over the serial framework, and the performance is greatly improved compared with the traversal selection method on large sparse matrices.

关键词： Deep learning Visualization Accuracy Costs Neural networks parallel processing Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

MPS: A Multiple Poisoned Samples Selection Strategy in Backdoor Attack

MPS: A Multiple Poisoned Samples Selection Strategy in Backd...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Weihong Zou Shigeng Zhang Weiping Wang Jian Zhang Xuan Liu Schoosl of Computer Science and Engineering Central South University Science and Technology on Parallel and Distributed Processing Laboratory (PDL) College of Computer Science and Electronic Engineering Hunan University

ISBN: (数字)9798350381993

ISBN: (纸本)9798350382006

Recently there has been many studies on backdoor attacks, which involve injecting poisoned samples into the training set in order to embed backdoors into the model. Existing multiple poisoned samples attacks usually randomly select a subset from clean samples to generate the poisoned samples. Filtering-and-Updating Strategy (FUS) has shown that the poisoning efficiency of each poisoned sample is inconsistent and random selection is not optimal. However, FUS does not fully considered the selection of multiple poisoned samples, there are still some issues with the selection of multiple poisoned samples. In this paper, we formulate the selection of multiple types of poisoned samples as a multi-objective optimization problem and proposed a Multiple Poisoned Samples Selection Strategy (MPS) to solve the issue. Unlike FUS, we consider the potential of clean samples that are not selected as to become efficient poisoned samples. Specifically, we use a weight-based contribution approach to calculate the contribution of each sample (clean sample and poisoned sample) during the training process from multiple dimensions. Finally, based on the greedy approach, we retain a subset of samples with the largest contribution in each dimension through iterations. We evaluate the effectiveness of MPS on various attack methods, including BadNet, Blended, ISSBA, and WaNet, as well as benchmark datasets. The experimental results on CIFAR-10 and GTSRB show that MPS can increase the attack strength by 1.45% to 18.34% compared to RSS and 0.43% to 10.84% compared to FUS in multiple poisoned samples attacks, thereby enhancing the stealthiness of the attack. Meanwhile, MPS is suitable for black-box settings, meaning that poisoned samples selected in one setting can be applied to other settings.

关键词： Training Data privacy Closed box Benchmark testing Security Protection Optimization

来源：评论

学校读者我要写书评

暂无评论

Merak: An Efficient distributed DNN Training Framework with Automated 3D parallelism for Giant Foundation Models

arXiv

引用

arXiv 2022年

作者： Lai, Zhiquan Li, Shengwei Tang, Xudong Ge, Keshi Liu, Weijie Duan, Yabo Qiao, Linbo Li, Dongsheng The National Laboratory for Parallel and Distributed Processing College of Computer National University of Defense Technology in Changsha Hunan China

Foundation models are in the process of becoming the dominant deep learning technology. Pretraining a foundation model is always time-consuming due to the large scale of both the model parameter and training dataset. Besides being computing-intensive, the pretraining process is extremely memory- and communication-intensive. These challenges make it necessary to apply 3D parallelism, which integrates data parallelism, pipeline model parallelism, and tensor model parallelism, to achieve high training efficiency. However, current 3D parallelism frameworks still encounter two issues: i) they are not transparent to model developers, requiring manual model modification to parallelize training, and ii) their utilization of computation resources, GPU memory, and network bandwidth is insufficient. We propose Merak, an automated 3D parallelism deep learning training framework with high resource utilization. Merak automatically deploys 3D parallelism with an automatic model partitioner, which includes a graph-sharding algorithm and proxy node-based model graph. Merak also offers a non-intrusive API to scale out foundation model training with minimal code modification. In addition, we design a high-performance 3D parallel runtime engine that employs several techniques to exploit available training resources, including a shifted critical path pipeline schedule that increases computation utilization, stage-aware recomputation that makes use of idle worker memory, and sub-pipelined tensor model parallelism that overlaps communication and computation. Experiments on 64 GPUs demonstrate Merak's capability to speed up training performance over state-of-the-art 3D parallelism frameworks of models with 1.5, 2.5, 8.3, and 20 billion parameters by up to 1.42, 1.39, 1.43, and 1.61×, respectively. The code for Merak has been open-sourced at https://***/hpdl-group/Merak. Copyright © 2022, The Authors. All rights reserved.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

SCGraph: Accelerating Sample-based GNN Training by Staged Caching of Features on GPUs

SCGraph: Accelerating Sample-based GNN Training by Staged Ca...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Yuqi He Zhiquan Lai Zhejiang Ran Lizhi Zhang Dongsheng Li National Key Laboratory of Parallel and Distributed Processing College of Computer National University of Defense Technology Changsha China

Graph neural networks (GNNs) have been becoming important tools for processing structured graph data and successfully applied to multiple graph-based application scenarios. The existing GNN systems adopt sample-based training on large-scale graphs over multiple GPUs. Although they support large-scale graph training, large data loading overhead of transferring vertex features between CPUs and GPUs is still a bottleneck. In this work, we propose SCGraph, a method that supports GPU high-speed feature caching. SCGraph classifies the graph vertices sorted by out-degrees. For high out-degree vertices, SCGraph sets grading caches via different GPUs to increase the overall cache content through NVLink high-speed data transmission between them. For low out-degree vertices, SCGraph expands training vertices' neighborhood in advance to regenerate cache. We evaluate SCGraph against two state-of-the-art industrial GNN frameworks, i.e., DGL and PaGraph on various benchmarks. Experimental results show that SCGraph improves the cache hit rate over GPUs up to 23.6%, and achieves up to 1.71x performance speedup over the state-of-the-art baselines while the convergence almost constant.

关键词： Training Memory management Loading Graphics processing units Benchmark testing Graph neural networks Data communication

来源：评论

学校读者我要写书评

暂无评论

Feature and Performance Comparison of FaaS Platforms 14

Feature and Performance Comparison of FaaS Platforms

引用

14th IEEE International Conference on Software Engineering and Service Science, ICSESS 2023

作者： Ma, Penghui Shi, Peichang Yi, Guodong College of Computer Science National University of Defense Technology National Key Laboratory of Parallel and Distributed Processing Changsha410073 China College of Computer Science National University of Defense Technology Key Laboratory of Software Engineering for Complex Systems Changsha410073 China Xiangjiang Lab Changsha410073 China School of Advanced Interdisciplinary Studies Hunan University of Technology and Business Changsha410073 China

ISBN: (纸本)9798350336269

With serverless computing offering more efficient and cost-effective application deployment, the diversity of serverless platforms presents challenges to users, including platform lock-in and costly migration. Moreover, due to the black box nature of function computing, traditional performance benchmarking methods are not applicable, necessitating new studies. This article presents a detailed comparison of six major public cloud function computing platforms and introduces a benchmarking framework for function computing performance. This framework aims to help users make comprehensive comparisons and select the most suitable platform for their specific needs. © 2023 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

AUXILIARY-TASKS LEARNING FOR PHYSICS-INFORMED NEURAL NETWORK-BASED PARTIAL DIFFERENTIAL EQUATIONS SOLVING

arXiv

引用

arXiv 2023年

作者： Yan, Junjun Chen, Xinhai Wang, Zhichao Zhou, Enqiang Liu, Jie Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha410073 China Laboratory of Digitizing Software for Frontier Equipment National University of Defense Technology Changsha410073 China

Physics-informed neural networks (PINNs) have emerged as promising surrogate modes for solving partial differential equations (PDEs). Their effectiveness lies in the ability to capture solution-related features through neural networks. However, original PINNs often suffer from bottlenecks, such as low accuracy and non-convergence, limiting their applicability in complex physical contexts. To alleviate these issues, we proposed auxiliary-task learning-based physics-informed neural networks (ATL-PINNs), which provide four different auxiliary-task learning modes and investigate their performance compared with original PINNs. We also employ the gradient cosine similarity algorithm to integrate auxiliary problem loss with the primary problem loss in ATL-PINNs, which aims to enhance the effectiveness of the auxiliary-task learning modes. To the best of our knowledge, this is the first study to introduce auxiliary-task learning modes in the context of physics-informed learning. We conduct experiments on three PDE problems across different fields and scenarios. Our findings demonstrate that the proposed auxiliary-task learning modes can significantly improve solution accuracy, achieving a maximum performance boost of 96.62% (averaging 28.23%) compared to the original single-task PINNs. The code and dataset are open source at https://***/junjun-yan/ATL-PINN. Copyright © 2023, The Authors. All rights reserved.

关键词： Partial differential equations

来源：评论

学校读者我要写书评

暂无评论

Bi-Objective Scheduling Algorithm for Hybrid Workflow in JointCloud

Bi-Objective Scheduling Algorithm for Hybrid Workflow in Joi...

引用

IEEE International Conference on Joint Cloud Computing (JCC)

作者： Rui Li Huaimin Wang Peichang Shi National Key Laboratory of Parallel and Distributed Processing College of Computer Science National University of Defense Technology Changsha China State Key Laboratory of Complex & Critica Software Environment College of Computer Science National University of Defense Technology Changsha China

ISBN: (数字)9798350387339

ISBN: (纸本)9798350387346

Big data workflows are widely used in IoT, recommended systems, and real-time vision applications, and they continue to grow in complexity. These hybrid workflows consist of both resource-intensive batch jobs and latency-sensitive stream jobs. Examples include the data analytics workflow, which incorporates batch data transformations and low-latency querying, and the machine learning workflow, which processes stream data feature extraction before performing batch training and low-latency inference. However, existing research on workflow scheduling primarily focuses on either stream or batch workflows, neglecting the efficient scheduling of hybrid workflows that respect their diverse resource requirements and the costly data transfers between *** this article, we propose a hybrid workflow model that defines the optimal placement of hybrid workflows (OHWP) as a bi-objective optimization problem. Our proposed model takes into account parameters related to inter-communication between stream and batch jobs, as well as the heterogeneous resources in JointCloud environment. Additionally, we present OHWP-PS (OHWP on a Pruned Space), a scheduling algorithm for hybrid workflows that minimizes both cost and latency by improving the initial population and dynamically updating the search space. The results demonstrate that the proposed OHWP-PS algorithm is effective and competitive across all experiments.

关键词： Training Scheduling algorithms Machine vision Heuristic algorithms Machine learning Feature extraction Remote working

来源：评论

学校读者我要写书评

暂无评论

ST-PINN: A Self-Training Physics-Informed Neural Network for Partial Differential Equations

arXiv

引用

arXiv 2023年

作者： Yan, Junjun Chen, Xinhai Wang, Zhichao Zhoui, Enqiang Liu, Jie Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha410073 China Laboratory of Digitizing Software for Frontier Equipment National University of Defense Technology Changsha410073 China

Partial differential equations (PDEs) are an essential computational kernel in physics and engineering. With the advance of deep learning, physics-informed neural networks (PINNs), as a mesh-free method, have shown great potential for fast PDE solving in various applications. To address the issue of low accuracy and convergence problems of existing PINNs, we propose a self-training physics-informed neural network, ST-PINN. Specifically, ST-PINN introduces a pseudo label based self-learning algorithm during training. It employs governing equation as the pseudo-labeled evaluation index and selects the highest confidence examples from the sample points to attach the pseudo labels. To our best knowledge, we are the first to incorporate a self-training mechanism into physics-informed learning. We conduct experiments on five PDE problems in different fields and scenarios. The results demonstrate that the proposed method allows the network to learn more physical information and benefit convergence. The ST-PINN outperforms existing physics-informed neural network methods and improves the accuracy by a factor of 1.33x-2.54x. The code of ST-PINN is available at GitHub: https://***/junjun-yan/ST-PINN. Copyright © 2023, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

A Fast Adversarial Sample Detection Approach for Industrial Internet-of-Things Applications

A Fast Adversarial Sample Detection Approach for Industrial ...

引用

International Workshop on Quality of Service

作者： Shigeng Zhang Yudong Li Shuxin Chen Xuan Li Jian Zhang School of Computer Science and Engineering Central South University College of Computer Science and Electronic Engineering Hunan University The Science and Technology on Parallel and Distributed Processing Laboratory (PDL) China

Adversarial attacks reveal the inherent vulnerability of deep neural networks, which face serious security issues for their security. Among them, the attack against the Deep Neural Network (DNN) application used in the Industrial Internet of Things (IIoT) is a key area in adversarial attacks. Adversarial examples generated by attackers by adding human-undetectable interference to legitimate examples may cause models to make wrong decision results, resulting in serious accidents. Many detection technologies have been proposed to mitigate the harm of adversarial examples to neural networks, among which the methods based on the difference of feature attribution between normal examples and adversarial examples show state-of-the-art detection performance, but they suffer from detection efficiency. In this work, we focus on improving the detection efficiency of the feature-attribution-based detection methods. We observe that there is still a significant difference in the feature attribution distribution of a normal image and an adversarial image even only some pixels in the image are processed, which can be verified by utilizing the Kolmogorov-Smirnov test. Based on this observation, we first adopt a variety of strategies to sample partial pixels in an image and then utilize the selected pixels to train a feature-attribution-based detector for detecting adversarial examples. Extensive experiments conducted on four datasets (MNIST, CIFAR-10, SVHN, CIFAR-100) against various attacks proved that the detection efficiency of the accelerated detection method is improved (for example, the average execution time was increased by 8.7 times on CIFAR-10) while the detection performance maintains state-of-the-art.

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：