检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Shu, Tianye Shang, Ke Gong, Cheng Nan, Yang Ishibuchi, Hisao Department of Computer Science and Engineering Southern University of Science and Technology China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Computer Science City University of Hong Kong Hong Kong

For a control problem with multiple conflicting objectives, there exists a set of Pareto-optimal policies called the Pareto set instead of a single optimal policy. When a multi-objective control problem is continuous and complex, traditional multiobjective reinforcement learning (MORL) algorithms search for many Pareto-optimal deep policies to approximate the Pareto set, which is quite resource-consuming. In this paper, we propose a simple and resource-efficient MORL algorithm that learns a continuous representation of the Pareto set in a high-dimensional policy parameter space using a single hypernet. The learned hypernet can directly generate various well-trained policy networks for different user preferences. We compare our method with two state-of-the-art MORL algorithms on seven multi-objective continuous robot control problems. Experimental results show that our method achieves the best overall performance with the least training parameters. An interesting observation is that the Pareto set is well approximated by a curved line or surface in a highdimensional parameter space. This observation will provide insight for researchers to design new MORL algorithms. © 2024, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

StyleAU: StyleGAN based Facial Action Unit Manipulation for Expression Editing

StyleAU: StyleGAN based Facial Action Unit Manipulation for ...

引用

IEEE International Joint Conference on Biometrics (IJCB)

作者： Yanliang Guo Xianxu Hou Feng Liu Linlin Shen Lei Wang Zhen Wang Peng Liu Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Qualcomm Technologies Inc

Facial expression editing has a wide range of applications, such as emotion detection, human-computer interaction, and social entertainment. However, existing expression editing methods either fail to allow for fine-grained editing, resulting in unnatural and unrealistic facial expressions, or generate artifacts and blurs, leading to poor image quality. In this paper, we propose a novel framework called StyleAU, which is based on StyleGAN and facial action units, to address these problems. Our framework leverages the pre-trained StyleGAN prior knowledge to enable action unit editing of the face in the StyleGAN latent space, allowing precise expression editing. In addition, we use an encoder to extract multi-scale content features to achieve high-fidelity image reconstruction. Our approach qualitatively and quantitatively outperforms competing methods for action unit manipulation and expression editing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Heuristic Algorithm for Precedence-Constrained Multi-Robot Task Assignment

Efficient Heuristic Algorithm for Precedence-Constrained Mul...

引用

第43届中国控制会议

作者： Xiaoshan Bai Baode Li Fuqiang Liu Li Qiu Guangzhong Cao College of Mechanical and Control Engineering Shenzhen University Guangdong Key Laboratory of Electromagnetic Control and Intelligent Robots Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University College of Mechanical and Vehicle Engineering Chongqing University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Due to the widespread application of multi-robot systems, the efficient task assignment for a team of robots has become particularly critical for performing complex tasks. This paper studies the task assignment problem for multiple robots to visit a group of target locations with precedence constraints, which determine the order/sequence in which certain target locations need to be visited before others. A marginal-cost-based heuristic algorithm is developed to minimize the time for the robots to visit the last target location. The algorithm first uses a timestamp strategy to update the anticipated visiting time of each assigned target and the corresponding earliest time that each successor target can be visited under the precedence constraints. Then, it utilizes the topological sorting technique and the marginal-cost-based mechanism to insert the feasible target that induces the minimum marginal cost into the robots' current routes. Numerical simulations demonstrate the effectiveness of the proposed algorithm compared with the popular greedy algorithm and the existing simple iterative auction algorithm.

关键词： Multi-robot task assignment Precedence constraints Heuristic algorithm Marginal cost

来源：评论

学校读者我要写书评

暂无评论

QoS-Aware and Cost-Efficient Dynamic Resource Allocation for Serverless ML Workflows

QoS-Aware and Cost-Efficient Dynamic Resource Allocation for...

引用

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Hao Wu Junxiao Deng Hao Fan Shadi Ibrahim Song Wu Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Inria Univ. Rennes CNRS IRISA France

Machine Learning (ML) workflows are increasingly deployed on serverless computing platforms to benefit from their elasticity and fine-grain pricing. Proper resource allocation is crucial to achieve fast and cost-efficient execution of serverless ML workflows (specially for hyperparameter tuning and model training). Unfortunately, existing resource allocation methods are static, treat functions equally, and rely on offline prediction, which limit their efficiency. In this paper, we introduce CE-scaling – a Cost-Efficient autoscaling framework for serverless ML work-flows. During the hyperparameter tuning, CE-scaling partitions resources across stages according to their exact usage to minimize resource waste. Moreover, it incorporates an online prediction method to dynamically adjust resources during model training. We implement and evaluate CE-scaling on AWS Lambda using various ML models. Evaluation results show that compared to state-of-the-art static resource allocation methods, CE-scaling can reduce the job completion time and the monetary cost by up to 63% and 41% for hyperparameter tuning, respectively; and by up to 58% and 38% for model training.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Denial-of-Service or Fine-Grained Control: Towards Flexible Model Poisoning Attacks on Federated Learning

arXiv

引用

arXiv 2023年

作者： Zhang, Hangtao Yao, Zeming Zhang, Leo Yu Hu, Shengshan Chen, Chao Liew, Alan Li, Zhetao School of Cyber Science and Engineering Huazhong University of Science and Technology China Swinburne University of Technology Australia Griffith University Australia National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab. Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China RMIT University Australia Xiangtan University China

Federated learning (FL) is vulnerable to poisoning attacks, where adversaries corrupt the global aggregation results and cause denial-of-service (DoS). Unlike recent model poisoning attacks that optimize the amplitude of malicious perturbations along certain prescribed directions to cause DoS, we propose a Flexible Model Poisoning Attack (FMPA) that can achieve versatile attack goals. We consider a practical threat scenario where no extra knowledge about the FL system (e.g., aggregation rules or updates on benign devices) is available to adversaries. FMPA exploits the global historical information to construct an estimator that predicts the next round of the global model as a benign reference. It then fine-tunes the reference model to obtain the desired poisoned model with low accuracy and small perturbations. Besides the goal of causing DoS, FMPA can be naturally extended to launch a fine-grained controllable attack, making it possible to precisely reduce the global accuracy. Armed with precise control, malicious FL service providers can gain advantages over their competitors without getting noticed, hence opening a new attack surface in FL other than DoS. Even for the purpose of DoS, experiments show that FMPA significantly decreases the global accuracy, outperforming six state-of-the-art attacks. © 2023, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Circular Decomposition and Cross-Modal Recombination for Multimodal Sentiment Analysis

Circular Decomposition and Cross-Modal Recombination for Mul...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Haijian Liang Weicheng Xie Xilin He Siyang Song Linlin Shen School of Computer Science & Software Engineering Computer Vision Institue Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University School of Computing and Mathematical Sciences University of Leicester National Engineering Laboratory for Big Data System Computing Technology Shenzhen University

Multimodal Sentiment Analysis is a burgeoning research area, leveraging various modalities to predict the sentiment score. Nevertheless, previous studies have disregarded the impact of noise interference on specific modal sentiments during video recording, thereby compromising the accuracy of sentiment prediction. In this paper, we propose the Guided Circular Decomposition and Cross-Modal Recombination (GCD-CMR) model, which aims to eliminate contaminated sentiment features in a fine-grained way. To achieve this, we utilize tailored global information specific to each modality to guide the circular decomposing process in the GCD module, to produce a set of sentiment prototypes. Subsequently, in the CMR module, we align cross-modal sentiment prototypes and remove the contaminated prototypes for recombination. Experimental results on two publicly available datasets demonstrate that our model surpasses state-of-the-art models, confirming the effectiveness of our proposed method. We release the code at: https://***/nianhua20/GCD-CMR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Four-Pronged Defense Against Byzantine Attacks in Federated Learning

arXiv

引用

arXiv 2023年

作者： Wan, Wei Hu, Shengshan Li, Minghui Lu, Jianrong Zhang, Longling Zhang, Leo Yu Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Federated learning (FL) is a nascent distributed learning paradigm to train a shared global model without violating users' privacy. FL has been shown to be vulnerable to various Byzantine attacks, where malicious participants could independently or collusively upload well-crafted updates to deteriorate the performance of the global model. However, existing defenses could only mitigate part of Byzantine attacks, without providing an all-sided shield for FL. It is difficult to simply combine them as they rely on totally contradictory assumptions. In this paper, we propose FPD, a four-pronged defense against both non-colluding and colluding Byzantine attacks. Our main idea is to utilize absolute similarity to filter updates rather than relative similarity used in existingI works. To this end, we first propose a reliable client selection strategy to prevent the majority of threats in the bud. Then we design a simple but effective score-based detection method to mitigate colluding attacks. Third, we construct an enhanced spectral-based outlier detector to accurately discard abnormal updates when the training data is not independent and identically distributed (non-IID). Finally, we design update denoising to rectify the direction of the slightly noisy but harmful updates. The four sequentially combined modules can effectively reconcile the contradiction in addressing non-colluding and colluding Byzantine attacks. Extensive experiments over three benchmark image classification datasets against four state-of-the-art Byzantine attacks demonstrate that FPD drastically outperforms existing defenses in IID and non-IID scenarios (with 30% improvement on model accuracy). © 2023, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Improving multi-view document clustering: leveraging multi-structure processor and hybrid ensemble clustering module 30

Improving multi-view document clustering: leveraging multi-s...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Bai, Ruina Bai, Qi Huang, Ruizhang Chen, Yanping Qin, Yongbin Text Computing & Cognitive Intelligence Engineering Research Center National Education Ministry College of Computer Science and Technology Guizhou University Guiyang550025 China State Key Laboratory of Public Big Data Guizhou University Guiyang550025 China School of Mathematical Sciences Zhejiang University Hangzhou310058 China

ISBN: (纸本)9782493814104

We introduce a multi-view document clustering model called DMsECN (Deep Multi-structure Ensemble Clustering Network), comprising a multi-structure processor and a hybrid ensemble clustering module. Unlike existing models, DMsECN distinguishes itself by creating a consensus structure from multiple clustering structures. The multi-structure processor comprises two stages, each contributing to the extraction of clustering structures that preserve both consistency and complementarity across multiple views. Representation learning extracts both view and view-fused representations from multi-views through the use of contrastive learning. Subsequently, multi-structure learning employs distinct view clustering guidance to generate the corresponding clustering structures. The hybrid ensemble clustering module merges two ensemble methods to amalgamate multiple structures, producing a consensus structure that guarantees both the separability and compactness of clusters within the clustering results. The attention-based ensemble primarily concentrates on learning the contribution weights of diverse clustering structures, while the similarity-based ensemble employs cluster assignment similarity and cluster classification dissimilarity to guide the refinement of the consensus structure. Experimental results demonstrate that DMsECN outperforms other models, achieving new state-of-the-art results on four multi-view document clustering datasets. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Structure (composition)

来源：评论

学校读者我要写书评

暂无评论

Adaptive Evolutionary Reinforcement Learning Algorithm with Early Termination Strategy 24

Adaptive Evolutionary Reinforcement Learning Algorithm with ...

引用

Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent systems

作者： Xiaoqiang Wu Qingling Zhu Qiuzhen Lin Weineng Chen Jianqiang Li College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China School of Computer Science and Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9798400704864

Evolutionary reinforcement learning algorithms (ERLs), which combine evolutionary algorithms (EAs) with reinforcement learning (RL), have demonstrated significant success in enhancing RL performance. However, most ERLs rely heavily on Gaussian mutation operators to generate new individuals. When the standard deviation is too large or small, this approach will result in the production of poor or highly similar offspring. Such outcomes can be detrimental to the learning process of the RL agent, as too many poor or similar experiences are generated by these individuals. In order to alleviate these issues, this paper proposes an Adaptive Evolutionary Reinforcement Learning (AERL) method that adaptively adjusts both the standard deviation and the evaluation process. By tracking the performance of new individuals, AERL maintains the mutation strength within a suitable range without the need for additional gradient computations. Moreover, the proposed AERL approach early terminates unnecessary evaluations and discards experiences arising from poor individuals, thereby resulting in enhanced learning efficiency. Empirical assessments conducted on a variety of continuous control problems demonstrate the effectiveness of the AERL method.

关键词： evolutionary algorithm evolutionary reinforcement learning reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Improving QoS of Workloads with CPU Pinning: A Deep Reinforcement Learning Approach

Improving QoS of Workloads with CPU Pinning: A Deep Reinforc...

引用

International Workshop on Quality of Service

作者： Xi Tao Weipeng Cao Yinghui Pan Ye Liu Zhong Ming Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen) Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (数字)9798350350128

ISBN: (纸本)9798350350135

In cloud computing, tenants tend to select predefined flavors with substantial resources that go beyond their needs, in order to avoid resource starvation. As a result, cloud service providers experience a high allocation ratio with a low utilization ratio of resources. To improve the resource utilization, cloud service providers offer lower-priced resources by building an overcommitted environment to reuse resources. However, the colocation interference of workloads in the overcommitted environment may cause performance anomalies and degrade quality of service (QoS). In this paper, we propose a real-time mechanism to pin a group of workloads to a certain subset of CPUs to increase resource utilization and minimize interference. To be specific, we leverage deep reinforcement learning (DRL) to automatically adjust the CPU pinning configuration in the overcommitted environment according to the performance of workloads.

关键词： Cloud computing Computational modeling Buildings Quality of service Interference Deep reinforcement learning Real-time systems

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：