检索结果-内蒙古大学图书馆

32nd International Conference on software engineering and Knowledge engineering, SEKE 2020

作者： Matcha, Wyao Touré, Fadel Badri, Mourad Badri, Linda Software Engineering Research Laboratory Department of Mathematics and Computer Science University of Quebec Trois- RivieresQC Canada

ISBN: (纸本)1891706500

This paper aims at investigating the use of deep learning to suggest candidate classes to be tested rigorously during unit testing. The approach is based on software unit testing information history and source code metrics. We conducted our experiments using data collected from five (5) successive versions of the open source Java Apache software system ANT. For each version, we collected various source code metrics from the source code of the Java classes. We then extracted testing coverage measures for software classes for which dedicated JUnit test classes have been developed. We considered instruction and method level coverage granularities. Based on the different datasets collected, we trained several deep neural network models. We validated the constructed classifiers using Cross Version Validation technique. The obtained results strongly support the viability of our approach with an average accuracy greater than 87%. © 2020 Knowledge Systems Institute Graduate School. All rights reserved.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

A Value-of-Information-based management framework for fog services

A Value-of-Information-based management framework for fog se...

引用

作者： Poltronieri, Filippo Tortonesi, Mauro Morelli, Alessandro Stefanelli, Cesare Suri, Niranjan Engineering Department University of Ferrara Ferrara Italy Department of Mathematics and Computer Science University of Ferrara Ferrara Italy Florida Institute for Human and Machine Cognition PensacolaFL United States United States Army Research Laboratory AdelphiMD United States

The management of fog computing applications is a challenging task that requires dealing with a dynamic and resource-scarce environment. We argue that approaches leveraging Value-of-Information (VoI) concepts and tools are particularly interesting to support the realization of that objective. This paper describes innovative methodologies and reference models for the service fabric management of fog computing services. First, we formalize the VoI concept and discuss its adoption in fog computing environments. Then, we propose a model that aims at maximizing the allocation of fog services from a value-based perspective. To overcome the complexity of this model, we present two possible solutions (a simplified user-specific VoI model and a distance-based heuristic), and we compare them by adopting meta-heuristics as optimization techniques. Then, we investigate the adoption of a hybrid model, which combines the distance-based heuristic with the simplified user-specific VoI model. Experimental results prove the validity of all presented approaches and highlight the soundness of the distance-based heuristic, which is capable of reaching the 91% performance of the simplified user-specific VoI model in a very short amount of time. This makes it a suitable approach for online optimization of resources in fog computing. © 2021 John Wiley & Sons, Ltd.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Algorithmic Stability of Heavy-Tailed Stochastic Gradient Descent on Least Squares 34

Algorithmic Stability of Heavy-Tailed Stochastic Gradient De...

引用

34th International Conference onAlgorithmic Learning Theory, ALT 2023

作者： Raj, Anant Barsbey, Melih Gürbüzbalaban, Mert Zhu, Lingjiong Şimşekli, Umut Coordinated Science Laboratory University of Illinois Urbana-Champaign Inria Ecole Normale Supérieure PSL Research University Paris France Department of Computer Engineering Bogaziçi University Istanbul Turkey Department of Management Science and Information Systems Rutgers University PiscatawayNJ United States Department of Mathematics Florida State University TallahasseeFL United States Inria CNRS Ecole Normale Supérieure PSL Research University Paris France

Recent studies have shown that heavy tails can emerge in stochastic optimization and that the heaviness of the tails have links to the generalization error. While these studies have shed light on interesting aspects of the generalization behavior in modern settings, they relied on strong topological and statistical regularity assumptions, which are hard to verify in practice. Furthermore, it has been empirically illustrated that the relation between heavy tails and generalization might not always be monotonic in practice, contrary to the conclusions of existing theory. In this study, we establish novel links between the tail behavior and generalization properties of stochastic gradient descent (SGD), through the lens of algorithmic stability. We consider a quadratic optimization problem and use a heavy-tailed stochastic differential equation (and its Euler discretization) as a proxy for modeling the heavy-tailed behavior emerging in SGD. We then prove uniform stability bounds, which reveal the following outcomes: (i) Without making any exotic assumptions, we show that SGD will not be stable if the stability is measured with the squared-loss x 7→ x2, whereas it in turn becomes stable if the stability is instead measured with a surrogate loss x 7→ |x|p with some p © 2023 A. Raj, M. Barsbey, M. Gürbüzbalaban, L. Zhu & U. Şimşekli.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

F2A2: flexible fully-decentralized approximate actor-critic for cooperative multi-agent reinforcement learning

The Journal of Machine Learning Research

引用

The Journal of Machine Learning research 2023年第1期24卷 8447-8521页

作者： Wenhao Li Bo Jin Xiangfeng Wang Junchi Yan Hongyuan Zha School of Data Science The Chinese University of Hong Kong Shenzhen Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of Software Engineering Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai China School of Computer Science and Technology Key Laboratory of Mathematics and Engineering Applications Ministry of Education East China Normal University Shanghai China Department of Computer Science and Engineering Key Laboratory of Artificial Intelligence Ministry of Education Shanghai Jiao Tong University Shanghai China

Traditional centralized multi-agent reinforcement learning (MARL) algorithms are sometimes unpractical in complicated applications due to non-interactivity between agents, the curse of dimensionality, and computation complexity. Hence, several decentralized MARL algorithms are motivated. However, existing decentralized methods only handle the fully cooperative setting where massive information needs to be transmitted in training. The block coordinate gradient descent scheme they used for successive independent actor and critic steps can simplify the calculation, but it causes serious bias. This paper proposes a exible fully decentralized actor-critic MARL framework, which can combine most of the actor-critic methods and handle large-scale general cooperative multi-agent settings. A primal-dual hybrid gradient descent type algorithm framework is designed to learn individual agents separately for decentralization. From the perspective of each agent, policy improvement and value evaluation are jointly optimized, which can stabilize multi-agent policy learning. Furthermore, the proposed framework can achieve scalability and stability for the large-scale environment. This framework also reduces information transmission by the parameter sharing mechanism and novel modeling-other-agents methods based on theory-of-mind and online supervised learning. Sufficient experiments in cooperative Multi-agent Particle Environment and StarCraft II show that the proposed decentralized MARL instantiation algorithms perform competitively against conventional centralized and decentralized methods.

关键词： cooperative MARL decentralized actor-critic primal-dual method

来源：评论

学校读者我要写书评

暂无评论

FedVC: Virtual Clients for Federated Autonomous Driving With Imbalanced Label Distribution

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Zhang, Yongquan Chen, Hongda Wang, Zhihui Kumar, Rahul Wang, Changmiao Zhejiang University of Finance and Economics School of Data Science Hangzhou310018 China Xi'an Jiaotong University School of Software Engineering Xi'an710049 China Shandong University of Science and Technology College of Computer Science and Engineering Qingdao266510 China Ssv Pg College Department Of Mathematics Hapur245101 India Shenzhen Research Institute of Big Data Shenzhen518172 China

Federated learning in autonomous driving safeguards the privacy of individual vehicles during collaborative training by avoiding the exchange of raw data. These vehicles often suffer from imbalanced label distribution, making the federated learning model developed from them critical for safety. Most current solutions addressing label imbalance in federated learning are oriented towards classification tasks. However, there is limited research focused on prediction tasks involving imbalanced datasets relevant to autonomous driving. To address the identified gap, we introduce an innovative peer-to-peer federated learning framework called FedVC. This framework includes the use of virtual clients to enhance the ability of the collaborative training process to recognize the global data distribution effectively. It strategically samples relevant segments of local data from various clients for each training round and controls the execution time for backpropagation associated with each virtual client. Importantly, FedVC constructs a global perspective by utilizing metadata from each client, thereby maintaining data privacy while overcoming the challenge of label imbalance in autonomous driving prediction tasks, all without the need to share any raw datasets. Experimental results demonstrate that FedVC outperforms classical FedAvg and the most recent methods at three steering angle prediction datasets with different levels of imbalanced label distribution. The source code is publicly available at https://***/aikedaerC/FedVC. © 1975-2011 IEEE.

关键词： Autonomous Driving Data Imbalance Federated Learning Virtual Clients

来源：评论

学校读者我要写书评

暂无评论

computer-Vision-Based Non-Contact Paste Concentration Measurement*

Computer-Vision-Based Non-Contact Paste Concentration Measur...

引用

Automation in Manufacturing, Transportation and Logistics (ICaMaL), International Conference on

作者： Tailin Liang Zhaolin Yuan State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing China Department of Industrial and Systems Engineering Research Institute of Advanced Manufacturing The Hong Kong Polytechnic University Hong Kong China

ISBN: (数字)9798350378658

ISBN: (纸本)9798350378665

For monitoring the paste concentration, existing techniques, such as ultrasonic concentration meters and neutron meters, suffer from radiation hazards and low precision in high concentrations. This paper proposes a novel non-contact concentration measurement method based on deep learning. With the dataset collected by preparing the paste with different concentrations and taking photographs from the paste surface, a convolutional neural network is trained to extract the features from images and predict the concentration. The experiments indicate that the measurement accuracy is close to 88.79 % for the manual stirring paste dataset and 91.42 % for the automatic stirring paste dataset, which are sufficient in industrial applications. As a substitution of traditional concentration measurement instruments, the proposed vision-based concentration measurement method is non-contact and its accuracy is sufficient in industrial applications.

关键词： Meters Deep learning Accuracy Ultrasonic variables measurement Transportation Manuals Feature extraction Surface texture Convolutional neural networks Surface treatment

来源：评论

学校读者我要写书评

暂无评论

EpiTESTER: Testing Autonomous Vehicles with Epigenetic Algorithm and Attention Mechanism

arXiv

引用

arXiv 2023年

作者： Lu, Chengjie Ali, Shaukat Yue, Tao The Department of Engineering Complex Software Systems Simula Research Laboratory Oslo0258 Norway Simula Research Laboratory Norway Oslo Metropolitan University Oslo0258 Norway The School of Computer Science and Engineering Beihang University Beijing100191 China

Testing autonomous vehicles (AVs) under various environmental scenarios that lead the vehicles to unsafe situations is known to be challenging. Given the infinite possible environmental scenarios, it is essential to find critical scenarios efficiently. To this end, we propose a novel testing method, named EpiTESTER, by taking inspiration from epigenetics, which enables species to adapt to sudden environmental changes. In particular, EpiTESTER adopts gene silencing as its epigenetic mechanism, which regulates gene expression to prevent the expression of a certain gene, and the probability of gene expression is dynamically computed as the environment changes. Given different data modalities (e.g., images, lidar point clouds) in the context of AV, EpiTESTER benefits from a multi-model fusion transformer to extract high-level feature representations from environmental factors and then calculates probabilities based on these features with the attention mechanism. To assess the cost-effectiveness of EpiTESTER, we compare it with a classical genetic algorithm (GA) (i.e., without any epigenetic mechanism implemented) and EpiTESTER with equal probability for each gene. We evaluate EpiTESTER with four initial environments from CARLA, an open-source simulator for autonomous driving research, and an end-to-end AV controller, Interfuser. Our results show that EpiTESTER achieved a promising performance in identifying critical scenarios compared to the baselines, showing that applying epigenetic mechanisms is a good option for solving practical problems. © 2023, CC BY.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Train faster, perform better: modular adaptive training in over-parameterized models 23

Train faster, perform better: modular adaptive training in o...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Yubin Shi Yixuan Chen Mingzhi Dong Xiaochen Yang Dongsheng Li Yujiang Wang Robert Dick Qin Lv Yingying Zhao Fan Yang Tun Lu Ning Gu Li Shang China and Shanghai Key Laboratory of Data Science School of Computer Science Fudan University School of Mathematics Statistics University of Glasgow Microsoft Research Asia Shanghai China Department of Engineering Science University of Oxford Department of Electrical Engineering and Computer Science University of Michigan Department of Computer Science University of Colorado Boulder School of Microelectronics Fudan University

Despite their prevalence in deep-learning communities, over-parameterized models convey high demands of computational costs for proper training. This work studies the fine-grained, modular-level learning dynamics of over-parameterized models to attain a more efficient and fruitful training strategy. Empirical evidence reveals that when scaling down into network modules, such as heads in self-attention models, we can observe varying learning patterns implicitly associated with each module's trainability. To describe such modular-level learning capabilities, we introduce a novel concept dubbed modular neural tangent kernel (mNTK), and we demonstrate that the quality of a module's learning is tightly associated with its mNTK's principal eigenvalue λmax. A large λmax indicates that the module learns features with better convergence, while those miniature ones may impact generalization negatively. Inspired by the discovery, we propose a novel training strategy termed Modular Adaptive Training (MAT) to update those modules with their λmax exceeding a dynamic threshold selectively, concentrating the model on learning common features and ignoring those superfluous ones. Unlike most existing training schemes with a complete BP cycle across all network modules, MAT can significantly save computations by its partially-updating strategy and can further improve performance. Experiments show that MAT nearly halves the computational cost of model training and outperforms the accuracy of baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Convex Ternary Quartics Are SOS-Convex

arXiv

引用

arXiv 2024年

作者： Ahmadi, Amir Ali Blekherman, Grigoriy Parrilo, Pablo A. The Department of Operations Research and Financial Engineering Princeton University United States The School of Mathematics The Georgia Institute of Technology United States The Laboratory for Information and Decision Systems The Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology United States

We show that if a ternary quartic form is convex, then it must be sos-convex;i.e, if the Hessian H(x) of a ternary quartic form is positive semidefinite for all x, then the biquadratic form yT H(x)y in the variables x:= (x1, x2, x3)T and y:= (y1, y2, y3)T must be a sum of squares. This result is in a meaningful sense the "convex analogue" of Hilbert’s celebrated theorem on ternary quartics. We show that exploiting the structure of the Hessian matrix is crucial in any possible proof of this result by presenting an explicit example of a biquadratic form b(x, y) that is symmetric in x and y, nonnegative, but not a sum of squares. © 2024, CC BY.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Once read is enough: domain-specific pretraining-free language models with cluster-guided sparse experts for long-tail domain knowledge 24

Once read is enough: domain-specific pretraining-free langua...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Fang Dong Mengyi Chen Jixian Zhou Yubin Shi Yixuan Chen Mingzhi Dong Yujiang Wang Dongsheng Li Xiaochen Yang Rui Zhu Robert Dick Qin Lv Fan Yang Tun Lu Ning Gu Li Shang China and Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Oxford Suzhou Centre for Advanced Research Suzhou China University of Bath and China and Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Microsoft Research Asia Shanghai China School of Mathematics & Statistics University of Glasgow Bayes Business School City St George's University of London Department of Electrical Engineering and Computer Science University of Michigan Department of Computer Science University of Colorado Boulder School of Microelectronics Fudan University

ISBN: (纸本)9798331314385

Language models (LMs) only pretrained on a general and massive corpus usually cannot attain satisfying performance on domain-specific downstream tasks, and hence, applying domain-specific pretraining to LMs is a common and indispensable practice. However, domain-specific pretraining can be costly and time-consuming, hindering LMs' deployment in real-world applications. In this work, we consider the incapability to memorize domain-specific knowledge embedded in the general corpus with rare occurrences and "long-tail" distributions as the leading cause for pretrained LMs' inferior downstream performance. Analysis of Neural Tangent Kernels (NTKs) reveals that those long-tail data are commonly overlooked in the model's gradient updates and, consequently, are not effectively memorized, leading to poor domain-specific downstream performance. Based on the intuition that data with similar semantic meaning are closer in the embedding space, we devise a Cluster-guided Sparse Expert (CSE) layer to actively learn long-tail domain knowledge typically neglected in previous pretrained LMs. During pretraining, a CSE layer efficiently clusters domain knowledge together and assigns long-tail knowledge to designate extra experts. CSE is also a lightweight structure that only needs to be incorporated in several deep layers. With our training strategy, we found that during pretraining, data of long-tail knowledge gradually formulate isolated, "outlier" clusters in an LM's representation spaces, especially in deeper layers. Our experimental results show that only pretraining CSE-based LMs is enough to achieve superior performance than regularly pretrained-finetuned LMs on various downstream tasks, implying the prospects of domain-specific-pretraining-free language models.

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：