检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Yao, Yuan Dong, Qingxiu Guan, Jian Cao, Boxi Zhang, Zhengyan Xiao, Chaojun Wang, Xiaozhi Qi, Fanchao Bao, Junwei Nie, Jinran Zeng, Zheni Gu, Yuxian Zhou, Kun Huang, Xuancheng Li, Wenhao Ren, Shuhuai Lu, Jinliang Xu, Chengqiang Wang, Huadong Zeng, Guoyang Zhou, Zile Zhang, Jiajun Li, Juanzi Huang, Minlie Yan, Rui He, Xiaodong Wan, Xiaojun Zhao, Xin Sun, Xu Liu, Yang Liu, Zhiyuan Han, Xianpei Yang, Erhong Sui, Zhifang Sun, Maosong Department of Computer Science and Technology Tsinghua University China MOE Key Lab of Computational Linguistics School of EECS Peking University China Institute of Software Chinese Academy of Sciences China JD AI Research Beijing China School of Information Science Beijing Language and Culture University China School of Information Renmin University of China China National Laboratory of Pattern Recognition Institute of Automation CAS China Gaoling School of Artificial Intelligence Renmin University of China China Wangxuan Institute of Computer Technology Peking University Beijing Academy of Artificial Intelligence China

Realizing general-purpose language intelligence has been a longstanding goal for natural language processing, where standard evaluation benchmarks play a fundamental and guiding role. We argue that for general-purpose language intelligence evaluation, the benchmark itself needs to be comprehensive and systematic. To this end, we propose CUGE, a Chinese Language Understanding and Generation Evaluation benchmark with the following features: (1) Hierarchical benchmark framework, where datasets are principally selected and organized with a language capability-task-dataset hierarchy. (2) Multilevel scoring strategy, where different levels of model performance are provided based on the hierarchical framework. To facilitate CUGE, we provide a public leaderboard that can be customized to support flexible model judging criteria. Evaluation results on representative pre-trained language models indicate ample room for improvement towards general-purpose language intelligence. CUGE is publicly available at ***. Copyright © 2021, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Global Momentum Compression for Sparse Communication in Distributed Learning

arXiv

引用

arXiv 2019年

作者： Shi, Chang-Wei Zhao, Shen-Yi Xie, Yin-Peng Gao, Hao Li, Wu-Jun National Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing210023 China

With the rapid growth of data, distributed momentum stochastic gradient descent (DMSGD) has been widely used in distributed learning, especially for training large-scale deep models. Due to the latency and limited bandwidth of the network, communication has become the bottleneck of distributed learning. Communication compression with sparsified gradient, abbreviated as sparse communication, has been widely employed to reduce communication cost. All existing works about sparse communication in DMSGD employ local momentum, in which the momentum only accumulates stochastic gradients computed by each worker locally. In this paper, we propose a novel method, called global momentum compression (GMC), for sparse communication. Different from existing works that utilize local momentum, GMC utilizes global momentum. Furthermore, to enhance the convergence performance when using more aggressive sparsification compressors (e.g., RBGS), we extend GMC to GMC+. We theoretically prove the convergence of GMC and GMC+. To the best of our knowledge, this is the first work that introduces global momentum for sparse communication in distributed learning. Empirical results demonstrate that, compared with the local momentum counterparts, our GMC and GMC+ can achieve higher test accuracy and exhibit faster convergence, especially under non-IID data distribution. Copyright © 2019, The Authors. All rights reserved.

关键词： Momentum

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey of orbital edge computing: Systems, applications, and algorithms

引用

Chinese Journal of Aeronautics 2025年第7期38卷

作者： Zengshan YIN Changhao WU Chongbin GUO Yuanchun LI Mengwei XU Weiwei GAO Chuanxiu CHI Chinese Academy of Sciences Shanghai Innovation Academy for Microsatellites Shanghai 201304 China University of Chinese Academy of Sciences Beijing 101408 China Institute for AI Industry Research (AIR) Tsinghua University Beijing 102200 China State Key Laboratory of Networking and Switching Technology Computer Science Department Beijing University of Posts and Telecommunications Beijing 100876 China

The number of satellites, especially those operating in Low-Earth Orbit (LEO), has been exploding in recent years. Additionally, the burgeoning development of Artificial Intelligence (AI) software and hardware has opened up new industrial opportunities in both air and space, with satellite-powered computing emerging as a new computing paradigm: Orbital Edge Computing (OEC). Compared to terrestrial edge computing, the mobility of LEO satellites and their limited communication, computation, and storage resources pose challenges in designing task-specific scheduling algorithms. Previous survey papers have largely focused on terrestrial edge computing or the integration of space and ground technologies, lacking a comprehensive summary of OEC architecture, algorithms, and case studies. This paper conducts a comprehensive survey and analysis of OEC’s system architecture, applications, algorithms, and simulation tools, providing a solid background for researchers in the field. By discussing OEC use cases and the challenges faced, potential research directions for future OEC research are proposed.

关键词： Orbital edge computing Ubiquitous computing Large-scale satellite constellations Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Driven Simultaneous Layout Decomposition and Mask Optimization

Deep Learning-Driven Simultaneous Layout Decomposition and M...

引用

Design Automation Conference

作者： Wei Zhong Shuxiang Hu Yuzhe Ma Haoyu Yang Xiuyuan Ma Bei Yu DUT-RU International School of Information Science & Engineering Dalian University of Technology China Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong SAR

ISBN: (数字)9781728110851

ISBN: (纸本)9781728158020

Combining multiple pattern lithography (MPL) and optical proximity correlation (OPC) pushes the limit of 193nm wavelength lithography to go further. Considering that layout decomposition may generate plenty of solutions with diverse printabilities, relying on conventional mask optimization process to select the best candidates for manufacturing is computationally expensive. Therefore, an accurate and efficient printability estimation is crucial and can significantly accelerate the layout decomposition and mask optimization (LDMO) process. In this paper, we propose a CNN based prediction and integrate it into our new high performance LDMO framework. We also develop both the layout and the decomposition sampling strategies to facilitate the network training. The experimental results demonstrate the effectiveness and the efficiency of the proposed algorithms.

关键词： Optimization Layout Lithography Estimation Training Multiprotocol label switching Optical distortion

来源：评论

学校读者我要写书评

暂无评论

Deep Multi-Index Hashing for Person Re-Identification

arXiv

引用

arXiv 2019年

作者： Li, Ming-Wei Jiang, Qing-Yuan Li, Wu-Jun National Key Laboratory for Novel Software Technology Collaborative Innovation Center of Novel Software Technology and Industrialization Department of Computer Science and Technology Nanjing University China

Traditional person re-identification (ReID) methods typically represent person images as real-valued features, which makes ReID inefficient when the gallery set is extremely large. Recently, some hashing methods have been proposed to make ReID more efficient. However, these hashing methods will deteriorate the accuracy in general, and the efficiency of them is still not high enough. In this paper, we propose a novel hashing method, called deep multi-index hashing (DMIH), to improve both efficiency and accuracy for ReID. DMIH seamlessly integrates multi-index hashing and multi-branch based networks into the same framework. Furthermore, a novel block-wise multi-index hashing table construction approach and a search-aware multi-index (SAMI) loss are proposed in DMIH to improve the search efficiency. Experiments on three widely used datasets show that DMIH can outperform other state-of-the-art baselines, including both hashing methods and real-valued methods, in terms of both efficiency and accuracy. Copyright © 2019, The Authors. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Transferring knowledge distillation for multilingual social event detection

arXiv

引用

arXiv 2021年

作者： Ren, Jiaqian Peng, Hao Jiang, Lei Wu, Jia Tong, Yongxin Wang, Lihong Bai, Xu Wang, Bo Yang, Qiang Institute of Information Engineering Chinese Academy of Sciences The School of Cyber Security University of Chinese Academy of Sciences Beijing100041 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100083 China The School of Cyber Science and Technology Beihang University Beijing100083 China Institute of Information Engineering Chinese Academy of Sciences Beijing100041 China The Department of Computing Macquarie University Sydney Australia The State Key Laboratory of Software Development Environment The School of Computer Science and Engineering Beihang University Beijing100083 China The National Computer Network Emergency Response Technical Team Coordination Center of China Beijing100029 China The Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong AI Group WeBank Co. Ltd. China

Recently published graph neural networks (GNNs) show promising performance at social event detection tasks. However, most studies are oriented toward monolingual data in languages with abundant training samples. This has left the more common multilingual settings and lesser-spoken languages relatively unexplored. Thus, we present a GNN that incorporates cross-lingual word embeddings for detecting events in multilingual data streams. The first exploit is to make the GNN work with multilingual data. For this, we outline a construction strategy that aligns messages in different languages at both the node and semantic levels. Relationships between messages are established by merging entities that are the same but are referred to in different languages. Non-English message representations are converted into English semantic space via the cross-lingual word embeddings. The resulting message graph is then uniformly encoded by a GNN model. In special cases where a lesser-spoken language needs to be detected, a novel cross-lingual knowledge distillation framework, called CLKD, exploits prior knowledge learned from similar threads in English to make up for the paucity of annotated data. Experiments on both synthetic and real-world datasets show the framework to be highly effective at detection in both multilingual data and in languages where training samples are scarce. © 2021, CC BY.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Data-driven Surplus Material Prediction in Steel Coil Production

Data-driven Surplus Material Prediction in Steel Coil Produc...

引用

International Conference on Wireless and Optical Communications ( WOCC)

作者： Ziyan Zhao Xiaoyue Yong Shixin Liu Mengchu Zhou State Key Laboratory of Synthetical Automation for Process Industries College of Information Science and Engineering Northeastern University Shenyang China Shanghai Baosight Software Co. Ltd Shanghai China Department of Electrical and Computer Engineering New Jersey Institute of Technology Newark USA

ISBN: (数字)9781728161242

ISBN: (纸本)9781728161259

A steel enterprise is currently trying to avoid the presence of surplus materials since they can greatly increase its operational cost. The complicated production process of steel products makes it difficult to find the causes of surplus materials. In this work, we propose a surplus material prediction problem and solve it based on statistical analysis and machine learning methods. In the concerned problem, we predict whether there are surplus materials under a given group of production parameters. The dataset used in this work is from a real-world three-month steel coil production process. First, data cleaning is conducted to standardize the industrial dataset. Then, the production parameters highly correlated with surplus material prediction results are selected by a series of feature selection methods. Finally, two prediction models based on extreme gradient boosting and logistic regression are presented according to the selected features. The experimental results reveal that the proposed prediction models have similar effectiveness. A visible regression function makes the logistic regression method more suitable for practical application.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Clustered reinforcement learning

arXiv

引用

arXiv 2019年

作者： Ma, Xiao Zhao, Shen-Yi Li, Wu-Jun National Key Laboratory for Novel Software Technology Collaborative Innovation Center of Novel Software Technology and Industrialization Department of Computer Science and Technology Nanjing University China

Exploration strategy design is one of the challenging problems in reinforcement learning (RL), especially when the environment contains a large state space or sparse rewards. During exploration, the agent tries to discover novel areas or high reward (quality) areas. In most existing methods, the novelty and quality in the neighboring area of the current state are not well utilized to guide the exploration of the agent. To tackle this problem, we propose a novel RL framework, called clustered reinforcement learning (CRL), for efficient exploration in RL. CRL adopts clustering to divide the collected states into several clusters, based on which a bonus reward reflecting both novelty and quality in the neighboring area (cluster) of the current state is given to the agent. Experiments on a continuous control task and several Atari 2600 games show that CRL can outperform other state-of-the-art methods to achieve the best performance in most cases. Copyright © 2019, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

On the Evaluation Metric for Hashing

arXiv

引用

arXiv 2019年

作者： Jiang, Qing-Yuan Li, Ming-Wei Li, Wu-Jun National Key Laboratory for Novel Software Technology Collaborative Innovation Center of Novel Software Technology and Industrialization Department of Computer Science and Technology Nanjing University China

Due to its low storage cost and fast query speed, hashing has been widely used for large-scale approximate nearest neighbor (ANN) search. Bucket search, also called hash lookup, can achieve fast query speed with a sub-linear time cost based on the inverted index table constructed from hash codes. Many metrics have been adopted to evaluate hashing algorithms. However, all existing metrics are improper to evaluate the hash codes for bucket search. On one hand, all existing metrics ignore the retrieval time cost which is an important factor reflecting the performance of search. On the other hand, some of them, such as mean average precision (MAP), suffer from the uncertainty problem as the ranked list is based on integer-valued Hamming distance, and are insensitive to Hamming radius as these metrics only depend on relative Hamming distance. Other metrics, such as precision at Hamming radius R, fail to evaluate global performance as these metrics only depend on one specific Hamming radius. In this paper, we first point out the problems of existing metrics which have been ignored by the hashing community, and then propose a novel evaluation metric called radius aware mean average precision (RAMAP) to evaluate hash codes for bucket search. Furthermore, two coding strategies are also proposed to qualitatively show the problems of existing metrics. Experiments demonstrate that our proposed RAMAP can provide more proper evaluation than existing metrics. Copyright © 2019, The Authors. All rights reserved.

关键词： Hamming distance

来源：评论

学校读者我要写书评

暂无评论

Weighted Linear Multiple Kernel Learning for Saliency Detection 2nd

Weighted Linear Multiple Kernel Learning for Saliency Detect...

引用

2nd EAI International Conference on Robotic Sensor Networks, ROSENET 2018

作者： Zhou, Quan Wu, Jinwen Fan, Yawen Zhang, Suofei Wu, Xiaofu Zheng, Baoyu Jin, Xin Lu, Huimin Latecki, Longin Jan National Engineering Research Center of Communications and Networking Nanjing University of Posts and Telecommunications Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China College of Information Engineering China University of Geosciences Wuhan China School of Internet of Things Nanjing University of Posts and Telecommunications Nanjing China National Engineering Research Center of Communications and Networking Nanjing University of Posts and Telecommunications Nanjing China Department of Cyber Security Beijing Electronic Science and Technology Institute Beijing China CETC Big Data Research Institute Co. Ltd. Guizhou Guiyang China Department of Mechanical and Control Engineering Kyushu Institute of Technology Kitakyushu Japan Department of Computer and Information Sciences Temple University PhiladelphiaPA United States

ISBN: (纸本)9783030177621

This paper presents a novel saliency detection method based on weighted linear multiple kernel learning (WLMKL), which is able to adaptively combine different contrast measurements in a supervised manner. Three commonly used bottom-up visual saliency operations are first introduced, including corner-surround contrast (CSC), center-surround contrast (CESC), and global contrast (GC). Then these contrast measures are fed into our WLMKL framework to produce the final saliency map. We show that the assigned weights for each contrast feature maps are always normalized in our WLMKL formulation. In addition, the proposed approach benefits from the advantages of the contribution of each individual contrast operation, and thus produces more robust and accurate saliency maps. The extensive experimental results show the effectiveness of the proposed model, and demonstrate the combination is superior to individual subcomponent. © 2020, Springer science and Business Media Deutschland GmbH. All rights reserved.

关键词： Center-surround contrast Corner-surround contrast Global contrast Multiple kernel learning Saliency detection

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：