检索结果-内蒙古大学图书馆

32nd ACM International Conference on Multimedia, MM 2024

作者： Bao, Yiying Zhou, Hao Peng, Chao Xu, Chenyang Shi, Shuo Cai, Kecheng East China Normal University Shanghai China Software Engineering Institute Shanghai Key Lab of Trustworthy Computing East China Normal University Shanghai China

ISBN: (纸本)9798400706868

In various domains such as transportation, resource management, and weather forecasting, there is an urgent need for methods that can provide predictions over a sufficiently long time horizon to encompass the period required for decision-making and implementation. Compared to traditional time series forecasting, ultra-long time series forecasting requires enhancing the model's ability to infer long time series, while maintaining inference costs within an acceptable range. To address this challenge, we propose the Boundary-Aware Periodicity-based sparsification strategy for Ultra-Long time series forecasting (BAP-UL).This method effectively captures periodic features in time series and reorganizes inputs and outputs into shorter sub-sequences for improved prediction accuracy. In the paper, we investigate several commonly used benchmark datasets and demonstrate that the proposed method can yield comparable performance across them. © 2024 ACM.

关键词： Weather forecasting

来源：评论

学校读者我要写书评

暂无评论

Sparsing and Smoothing for the seq2seq Models

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第3期4卷 464-472页

作者： Zhao, Shuai Liang, Zhuoqian Wen, Jinming Chen, Jie College of Information Science and Technology Jinan University Guangzhou511400 China Pazhou Lab Guangzhou510330 China Shanghai Key Laboratory of Trustworthy Computing School of Software Engineering East China Normal University Shanghai200062 China

Current neural language models are trained to minimize cross-entropy and use softmax to compute the locally normalized probabilities over the target. While this setup provides solid results in several natural language processing (NLP) tasks, one unsatisfying aspect is its dense output. This density is wasteful, making models hard to interpret and assigning probability mass to many implausible outputs. To overcome this problem, we propose T-softmax, a simple but effective method to draw considerably sparse probability out of neural language models than softmax. Our method avoids dense output by truncating the unreliable tail of the probability distribution to improve the model's performance. In addition, we generalize logits with temperature, a critical regularization technique, from the softmax to T-softmax. To show our approach as a drop-in replacement for softmax, we evaluate them on three NLP tasks: summary generation, question answer, and math word problem. Experimental results show that our proposed model significantly improves performance without sacrificing speed;notably, in all experiments, our method outperforms the softmax. © 2020 IEEE.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

Green Federated Learning over Cloud-RAN with Limited Fronthaul and Quantized Neural Networks 3

Green Federated Learning over Cloud-RAN with Limited Frontha...

引用

3rd IEEE International Mediterranean Conference on Communications and Networking, MeditCom 2023

作者： Wang, Jiali Mao, Yijie Wang, Ting Shi, Yuanming Shanghai Key Lab. of Trustworthy Computing East China Normal University MoE Engineering Research Center of Software/Hardware Co-Design Technology and Application China China

ISBN: (纸本)9798350333732

In this paper, we investigate a green federated learning (FL) framework over cloud radio access network (Cloud-RAN) system that comprises a server, multiple devices and remote radio heads (RRHs). Each device utilizes quantized neural networks (QNNs) and sends quantized model parameters to the server to save energy consumption via RRHs. The server aggregates all the signals to update the global model parameters and broadcasts the updated parameters to the selected devices. In this context, we propose an energy consumption model for the QNN training and communication model over Cloud-RAN. We develop an energy minimization problem based on the proposed energy model. We jointly design fronthaul rate allocation, device transmit power, and precision level of QNNs while ensuring target accuracy, transmit power budget and limited fronthaul capacity. Guided by the convergence analysis, we adopt alternative optimization method to solve the energy minimization problem. The simulation outcomes demonstrate that the FL framework suggested can considerably diminish energy usage in comparison to other traditional methods. This has immense potential in realizing a sustainable and eco-friendly FL over Cloud-RAN. © 2023 IEEE.

关键词： Radio access networks

来源：评论

学校读者我要写书评

暂无评论

A novel spatio-temporal trajectory data-driven development approach for autonomous vehicles

引用

Frontiers of Earth Science 2021年第3期15卷 620-630页

作者： Menghan ZHANG Mingjun MA Jingying ZHANG Mingzhuo ZHANG Bo LIW Dehui DU School of Software and Engineering East China Normal UniversityShanghai 200062China Shanghai Key Laboratory of Trustworthy Computing East China Normal UniversityShanghai 200062China MOE International Joint Lab of Trustworthy Software East China Normal UniversityShanghai 200062China

Nowadays,autonomous driving has been attracted widespread attention from academia and *** we all know,deep learning is effective and essential for the development of AI components of Autonomous Vehicles(AVs).However,it is challenging to adopt multi-source heterogenous data in deep ***,we propose a novel data-driven approach for the delivery of high-quality Spatio-Temporal Trajectory Data(STTD)to AVs,which can be deployed to assist the development of AI components with deep *** novelty of our work is that the meta-model of STTD is constructed based on the domain knowledge of autonomous *** approach,including collection,preprocessing,storage and modeling of STTD as well as the training of AI components,helps to process and utilize huge amount of STTD *** further demonstrate the usability of our approach,a case study of vehicle behavior prediction using Long Short-Term Memory(LSTM)networks is *** results show that our approach facilitates the training process of AI components with the STTD.

关键词： spatio-temporal trajectory data data metamodeling domain knowledge LSTM vehicle behavior prediction AI component

来源：评论

学校读者我要写书评

暂无评论

SuperDetector: A Framework for Performance Detection on Vulnerabilities of Smart Contracts 6

SuperDetector: A Framework for Performance Detection on Vuln...

引用

2022 6th International Conference on Data Mining, Communications and Information Technology, DMCIT 2022

作者： Dai, Meiyi Yang, Zhe Guo, Jian Software/Hardware Co-design Technology and Application Engineering Research Center East China Normal University China Shanghai Key Lab for Trustworthy Computing East China Normal University China

The technology of Ethereum blockchain enables the implementation of smart contracts. Nowadays smart contracts are one of the most successful applications of blockchain technology, which are widely used in many fields, such as finance, energy and services. The decentralization and immutability properties of Ethereum blockchain provide security for transactions from smart contracts. However, these properties are possible to lead to unfixable vulnerabilities of smart contracts. In recent years, vulnerability detection on smart contracts has attracted more attention from researchers and many related tools have emerged. Nevertheless, the existing vulnerability detection tools have not yet been put into formal use. Due to the lack of suitable smart contract sets and fair metrics with other factors, it remains complex work to conduct authoritative performance tests on these tools. In this paper, we first summarize eight common vulnerabilities of smart contracts, and then divide them into call-related and call-irrelated vulnerabilities according to whether they involve caller functions or not. In addition, we propose a detection framework called SuperDetector, which combines a variety of vulnerability detection tools based on static analysis technology. And the framework mainly measures the detection performance, which contains vulnerability coverage, detection accuracy, usability and execution time on the two types of vulnerabilities. The results indicate that the framework can analyze the performance from different perspectives, and the performance of vulnerability coverage and detection accuracy on call-related vulnerabilities is much better than that on call-irrelated vulnerabilities. Finally, we design a selector based on the detection results in the framework for improving the vulnerability coverage and detection accuracy. © Published under licence by IOP Publishing Ltd.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Model Checking Quantum Continuous-Time Markov Chains 32

Model Checking Quantum Continuous-Time Markov Chains

引用

32nd International Conference on Concurrency Theory, CONCUR 2021

作者： Xu, Ming Mei, Jingyi Guan, Ji Yu, Nengkun MoE Engineering Research Center of Software/Hardware Co-design Technology and Application Shanghai Key Lab of Trustworthy Computing East China Normal University Shanghai China Shanghai Key Lab of Trustworthy Computing East China Normal University Shanghai China State Key Lab of Computer Science Institute of Software Chinese Academy of Sciences Beijing China Centre for Quantum Software and Information Faculty of Engineering and Information Technology University of Technology Sydney Australia

ISBN: (纸本)9783959772037

Verifying quantum systems has attracted a lot of interests in the last decades. In this paper, we initialise the model checking of quantum continuous-time Markov chain (QCTMC). As a real-time system, we specify the temporal properties on QCTMC by signal temporal logic (STL). To effectively check the atomic propositions in STL, we develop a state-of-the-art real root isolation algorithm under Schanuel's conjecture;further, we check the general STL formula by interval operations with a bottom-up fashion, whose query complexity turns out to be linear in the size of the input formula by calling the real root isolation algorithm. A running example of an open quantum walk is provided to demonstrate our method. © Ming Xu, Jingyi Mei, Ji Guan, and Nengkun Yu;.

关键词： Model checking

来源：评论

学校读者我要写书评

暂无评论

Requirements Modeling Aided by ChatGPT: An Experience in Embedded Systems

Requirements Modeling Aided by ChatGPT: An Experience in Emb...

引用

IEEE International Requirements engineering Conference Workshops (REW)

作者： Kun Ruan Xiaohong Chen Zhi Jin Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai China School of Computer Science Peking University China Ministry of Education Key Lab. of High-Confidence of Software Technologies (PKU) China

Requirements modeling is a crucial tool for requirements analysis and has been demonstrated to aid in the comprehension and analysis of requirements. However, constructing requirements models from natural language descriptions in user requirements documents can be a time-consuming task. With the growing attention given to large language models, they have become an integral component of natural language processing. Consequently, utilizing large language models to facilitate the construction of high-quality requirement models is appealing. This paper presents an automated framework for requirement model generation that incorporates ChatGPT-based zero-shot learning to extract requirement models from requirement texts and subsequently compose them using predefined rules. The framework defines the requirement extraction task of ChatGPT by designing appropriate prompt, and it generates requirement models by employing composition rules. Furthermore, a case study on a digital home system is conducted to validate the feasibility of the framework in assisting requirements modeling.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient Workflow Scheduling Over Yarn Cluster Using Deep Reinforcement Learning

Towards Efficient Workflow Scheduling Over Yarn Cluster Usin...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Jianguo Xue Ting Wang Puyu Cai MoE Engineering Research Center of Software/Hardware Co-design Technology and Application Shanghai Key Lab. of Trustworthy Computing East China Normal University China Department of Computer Science and Engineering Michigan State University USA

Hadoop Yarn is an open-source cluster manager responsible for resource management and job scheduling. However, data-driven applications are typically organized into workflows that consist of a series of jobs with dependencies. Yarn does not manage users' workflows and only considers the current job rather than the entire workflow when scheduling. In practice, multiple workflows share the same Yarn cluster and are pre-assigned separate Yarn resource queues to avoid mutual interference. However, this coarse-grained resource division can sometimes result in low resource utilization and increased pending time of jobs on the Yarn queue. For instance, one resource queue may have exhausted its quota while still having pending jobs, while other queues may have availab.e resources but cannot begin executing any jobs due to unfulfilled data dependencies. To address this problem, we propose a deep reinforcement learning-based workflow scheduling scheme that takes into account job dependencies, job priorities, and dynamic resource usage. The proposed approach can intelligently identify and utilize free windows of different resource queues. Our simulation results demonstrate that the proposed DRL-based workflow scheduling scheme can significantly reduce the average job latency compared to existing approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Federated Linear Bandit Learning via Over-the-air Computation

arXiv

引用

arXiv 2023年

作者： Wang, Jiali Jiang, Yuning Liu, Xin Wang, Ting Shi, Yuanming MoE Engineering Research Center of Software/Hardware Co-design Technology and Application Shanghai Key Lab. of Trustworthy Computing East China Normal University China Automatic Control Laboratory EPFL Switzerland ShanghaiTech University China

In this paper, we investigate federated contextual linear bandit learning within a wireless system that comprises a server and multiple devices. Each device interacts with the environment, selects an action based on the received reward, and sends model updates to the server. The primary objective is to minimize cumulative regret across all devices within a finite time horizon. To reduce the communication overhead, devices communicate with the server via over-the-air computation (AirComp) over noisy fading channels, where the channel noise may distort the signals. In this context, we propose a customized federated linear bandits scheme, where each device transmits an analog signal, and the server receives a superposition of these signals distorted by channel noise. A rigorous mathematical analysis is conducted to determine the regret bound of the proposed scheme. Both theoretical analysis and numerical experiments demonstrate the competitive performance of our proposed scheme in terms of regret bounds in various settings. © 2023, CC BY-NC-SA.

关键词： Fading channels

来源：评论

学校读者我要写书评

暂无评论

Green Federated Learning over Cloud-RAN with Limited Fronthaul and Quantized Neural Networks

Green Federated Learning over Cloud-RAN with Limited Frontha...

引用

Communications and Networking (MeditCom), IEEE International Mediterranean Conference on

作者： Jiali Wang Yijie Mao Ting Wang Yuanming Shi MoE Engineering Research Center of Software/Hardware Co-Design Technology and Application Shanghai Key Lab. of Trustworthy Computing East China Normal University China School of Information Science and Technology (SIST) ShanghaiTech University China

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：