检索结果-内蒙古大学图书馆

33rd ACM Web Conference, WWW 2024

作者： Lin, Xin Su, Tianhuang Huang, Zhenya Xue, Shangzi Liu, Haifeng Chen, Enhong School of Computer Science and Technology University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China Guangdong OPPO Mobile Telecommunications Corp. Ltd Shenzhen China University of Science and Technology of China Hefei China Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China

ISBN: (纸本)9798400701719

Knowledge-based question answering (KBQA) is a key task in natural language processing research, and also an approach to access the web data and knowledge, which requires exploiting knowledge graphs (KGs) for reasoning. In the literature, one promising solution for KBQA is to incorporate the pretrained language model (LM) with KGs by generating KG-centered pretraining corpus, which has shown its superiority. However, these methods often depend on specific techniques and resources to work, which may not always be available and restrict its application. Moreover, existing methods focus more on improving language understanding with KGs, while neglect the more important human-like complex reasoning. To this end, in this paper, we propose a general K nowledge-I njected C urriculum P retraining framework (KICP) to achieve comprehensive KG learning and exploitation for KBQA tasks, which is composed of knowledge injection (KI), knowledge adaptation (KA) and curriculum reasoning (CR). Specifically, the KI module first injects knowledge into the LM by generating KG-centered pretraining corpus, and generalizes the process into three key steps that could work with different implementations for flexible application. Next, the KA module learns knowledge from the generated corpus with LM equipped with an adapter as well as keeps its original natural language understanding ability to reduce the negative impacts of the difference between the generated and natural corpus. Last, to enable the LM with complex reasoning, the CR module follows human reasoning patterns to construct three corpora with increasing difficulties of reasoning, and further trains the LM from easy to hard in a curriculum manner to promote model learning. We provide an implementation of the general framework, and evaluate the proposed KICP on four real-word datasets. The results demonstrate that our framework can achieve higher performances, and have good generalization ability to other QA tasks. © 2024 ACM.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Research on Backward Cloud Transformation Algorithm Based on Adding Cloud Drops 9

Research on Backward Cloud Transformation Algorithm Based on...

引用

9th International Conference on Fuzzy Systems and data Mining, FSDM 2023

作者： Xu, Changlin Kong, Lingzhuo School of Mathematics and Information Science North Minzu University Yinchuan750021 China The Key Laboratory of Intelligent Information and Big Data Processing of Ning Xia Province Yinchuan750021 China

ISBN: (纸本)9781643684703

As a tool for studying uncertain information, cloud model is of great significance in uncertain artificial intelligence and data mining. Among them, the backward cloud transformation method is one of the important algorithms of cloud model, which can realize the conversion from quantitative data to qualitative concepts. In this paper, a dynamic incremental backward cloud transformation algorithm is proposed to solve the problem that the estimated value of hyper entropy is imaginary when the backward cloud transformation method is used to calculate hyper entropy. First, according to the formation characteristics of cloud drops, the generated samples and the original samples are fused as new samples by dynamically and randomly generating samples, and then the hyper entropy is estimated until the estimated value of hyper entropy is real. Secondly, the stability and convergence of the algorithm proposed in this paper are analyzed through simulation experiments. The experimental results show that the new dynamic incremental backward cloud transformation algorithm solves the problem that the hyper entropy estimation value is imaginary while the estimation error is small and the stability is good. Finally, the algorithm is applied to brain CT segmentation, and the results show that the algorithm is effective and practical. © 2023 The authors and IOS Press.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional architecture using hollow Cu/C nanofiber interpenetrated with MXenes for high-rate lithium-ion batteries

引用

Rare Metals 2023年第10期42卷 3378-3386页

作者： Jing-Chong Liu Lin-Lin Ma Shuai Li Lan-Lan Hou Xin-Ran Qi Yong-Qiang Wen Guo-Ping Hu NüWang Yong Zhao Xiao-Xian Zhao Beijing Key Laboratory for Bioengineering and Sensing Technology Daxing Research InstituteSchool of Chemistry and Biological EngineeringUniversity of Science and Technology BeijingBeijing100083China Key Laboratory of Intelligent Textile and Flexible Interconnection of Zhejiang Province Hangzhou310018China Department of Chemistry College of ScienceHebei Agriculture UniversityBaoding071001China School of Chemistry Beihang UniversityBeijing100191China Key Laboratory of Rare Earths Ganjiang Innovation AcademyChinese Academy of SciencesGanzhou341119China

Improving the electron/ion transport ability and alleviating expansion during charging/discharging processes are vital for lithium-ion batteries(LIBs).In this work,a three-dimensional anode was fabricated using conductive hollow carbon-based nano tubes interpenetrated MXene architecture by directing the assembly of flexible electrospun hollow copper/carbon nanotubes and rigid Ti_(3)C_(2)T_(x) MXene *** introduction of copper into carbon matrix leads to an improvement of lithium storage owing to the increase of disorder ***,the unique structure of the fabricated electrode provides a cross-network for fast electron diffusion by preventing the stack of nanotubes and MXene ***,the optimized electrode exhibits a high initial capacity of 424.45mAh·g^(-1) and maintains at 378.05 mAh·g^(-1) with a current density of 5 A·g^(-1) after 1000 *** strategy of structural and chemical optimization provides new ideas for developing high-performance and durable electrochemical energy storage devices in the future.

关键词： Nanofiber Hollow structure Electrospinning Carbon materials Lithium-ion battery

来源：评论

学校读者我要写书评

暂无评论

GoPIM: GCN-Oriented Pipeline Optimization for PIM Accelerators 31

GoPIM: GCN-Oriented Pipeline Optimization for PIM Accelerato...

引用

31st IEEE International Symposium on High Performance Computer Architecture, HPCA 2025

作者： Yang, Siling He, Shuibing Wang, Wenjiong Yin, Yanlong Wu, Tong Chen, Weijian Zhang, Xuechen Sun, Xian-He Feng, Dan The State Key Laboratory of Blockchain and Data Security Zhejiang University China Zhejiang Lab China Institute of Blockchain and Data Security China Zhejiang Key Laboratory of Big Data Intelligent Computing China Washington State University Vancouver United States Illinois Institute of Technology United States Huazhong University of Science and Technology China Wuhan National Laboratory for Optoelectronics China

ISBN: (纸本)9798331506476

Graph convolutional networks (GCNs) are popular for a variety of graph learning tasks. ReRAM-based processing-in-memory (PIM) accelerators are promising to expedite GCN training owing to their in-situ computing capability. However, existing accelerators can be severely underutilized even with pipelines, due to the oversight of the skewed execution times of various GCN stages and the ignorance of skewed degrees of graph vertices. In this work, we propose GOPIM, a GCN-oriented pipeline optimization for PIM accelerators to expedite GCN training. First, GOPIM proposes an ML-based scheme that allocates crossbar resources to the most needed stages to streamline the overall pipeline. Second, GOPIM utilizes a selective vertex updating technique that evenly distributes vertices on crossbars by interleaved mapping. These techniques collectively reduce the overall execution time without losing much accuracy. We also provide a practical architecture design for GOPIM. Our experimental results show that, GoPIM achieves up to 191 × speedup and 16.1 × energy saving, compared to the state-of-the-art work. © 2025 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Ancient Character Recognition: A Novel Image dataset of Shui Manuscript Characters and Classification Model

引用

Chinese Journal of Electronics 2023年第1期32卷 64-75页

作者： TANG Minli XIE Shaomin LIU Xiangrong Department of Computer Science and Technology School of Informatics Xiamen University School of Big Data Engineering KaiLi University Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Ministry of Culture and Tourism Xiamen University

Shui manuscripts are part of the national intangible cultural heritage of China. Owing to the particularity of text reading, the level of informatization and intelligence in the protection of Shui manuscript culture is not adequate. To address this issue, this study created Shuishu＿C, the largest image dataset of Shui manuscript characters that has been reported. Furthermore, after extensive experimental validation, we proposed ShuiNet-A,a lightweight artificial neural network model based on the attention mechanism, which combines channel and spatial dimensions to extract key features and finally recognize Shui manuscript characters. The effectiveness and stability of ShuiNet-A were verified through multiple sets of experiments. Our results showed that, on the Shui manuscript dataset with 113 categories, the accuracy of ShuiN et-A was 99.8%, which is 1.5% higher than those of similar studies. The proposed model could contribute to the classification accuracy and protection of ancient Shui manuscript characters.

关键词： Training Speech recognition Artificial neural networks Feature extraction Stability analysis Character recognition Machine translation

来源：评论

学校读者我要写书评

暂无评论

AdaptSSR: Pre-training User Model with Augmentation-Adaptive Self-Supervised Ranking 37

AdaptSSR: Pre-training User Model with Augmentation-Adaptive...

引用

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Yu, Yang Liu, Qi Zhang, Kai Zhang, Yuren Song, Chao Hou, Min Yuan, Yuqing Ye, Zhihao Zhang, Zaixi Yu, Sanshi Lei Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence China OPPO Research Institute China Hefei University of Technology China

ISBN: (纸本)9781713899921

User modeling, which aims to capture users' characteristics or interests, heavily relies on task-specific labeled data and suffers from the data sparsity issue. Several recent studies tackled this problem by pre-training the user model on massive user behavior sequences with a contrastive learning task. Generally, these methods assume different views of the same behavior sequence constructed via data augmentation are semantically consistent, i.e., reflecting similar characteristics or interests of the user, and thus maximizing their agreement in the feature space. However, due to the diverse interests and heavy noise in user behaviors, existing augmentation methods tend to lose certain characteristics of the user or introduce noisy behaviors. Thus, forcing the user model to directly maximize the similarity between the augmented views may result in a negative transfer. To this end, we propose to replace the contrastive learning task with a new pretext task: Augmentation-Adaptive Self-Supervised Ranking (AdaptSSR), which alleviates the requirement of semantic consistency between the augmented views while pre-training a discriminative user model. Specifically, we adopt a multiple pairwise ranking loss which trains the user model to capture the similarity orders between the implicitly augmented view, the explicitly augmented view, and views from other users. We further employ an in-batch hard negative sampling strategy to facilitate model training. Moreover, considering the distinct impacts of data augmentation on different behavior sequences, we design an augmentation-adaptive fusion mechanism to automatically adjust the similarity order constraint applied to each sample based on the estimated similarity between the augmented views. Extensive experiments on both public and industrial datasets with six downstream tasks verify the effectiveness of AdaptSSR. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Tensor Graph Convolutional Network for Dynamic Graph Representation Learning 7

Tensor Graph Convolutional Network for Dynamic Graph Represe...

引用

7th International Symposium on Autonomous Systems, ISAS 2024

作者： Wang, Ling Yuan, Ye The School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China The Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Engineering Research Center of Big Data Application For Smart Cities Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China College of Computer and Information Science Southwest University Chongqing400715 China

ISBN: (纸本)9798350363173

Dynamic graphs (DG) represent evolving interactions between entities in various real-world scenarios. Many existing DG representation learning models employ a combination of graph convolutional networks and sequence neural networks to capture spatial-temporal dependencies. However, this hybrid approach often fails to effectively capture the spatial-temporal continuity inherent in DGs. In this paper, we propose a novel approach called the Tensor Graph Convolutional Network (TGCN) to learn DG representations within a unified convolution framework based on tensor products. Our approach is founded on two key principles: (a) representing DG information in tensor form, and (b) leveraging tensor product operations to design a graph convolutional network that simultaneously models spatial and temporal features. Experimental results on three real-world DG datasets demonstrate that our proposed model achieves state-of-the-art performance. © 2024 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Novel camera self-calibration method with clustering prior and nonlinear optimization from an image sequence

引用

Multimedia Tools and Applications 2024年第42期83卷 90553-90572页

作者： Jiang, Xiaohui Zhu, Haijiang An, Ning Xie, Binjian Wei, Hao Tang, Fulin Wu, Yihong College of Information Science and Technology Beijing University of Chemical Technology Beijing100029 China State Key Laboratory of Multimodal Artificial Intelligence Institute of Automation Chinese Academy of Sciences Beijing100190 China State Key Laboratory of Intelligent Coal Mining and Strata Control Beijing100013 China Research Institute of Mine Big Data China Coal Research Institute Beijing100013 China

In many 3D reconstruction, Simultaneous Localization and Mapping (SLAM), AR, and VR systems, the camera focal length constantly changes slightly due to loose hardware, causing their performances to deteriorate. To address this problem, we propose a novel camera self-calibration method that incorporates clustering prior and nonlinear optimization. By leveraging the Kruppa equation, we roughly estimate multiple analytical solutions for the camera focal length from an image sequence. Then, robust clustering based on the Gaussian mixture model is introduced to obtain an initial camera focal length value. Finally, a nonlinear cost function is proposed to refine the initial camera focal length value. Extensive experimental results on simulation and real data demonstrate that the proposed method outperforms the state-of-the-art methods, exhibiting good robustness and high accuracy. Moreover, the proposed method can be used in real-time videos for SLAM systems. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Plausible Heterogeneous Graph k-Anonymization for Social Networks

引用

Tsinghua science and technology 2022年第6期27卷 912-924页

作者： Kaiyang Li Ling Tian Xu Zheng Bei Hui School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu 610054China Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province Chengdu 610000China

The inefficient utilization of ubiquitous graph data with combinatorial structures necessitates graph embedding methods,aiming at learning a continuous vector space for the graph which is amenable to be adopted in traditional machine learning algorithms in favor of vector *** embedding methods build an important bridge between social network analysis and data analytics as social networks naturally generate an unprecedented volume of graph data *** social network data not only bring benefit for public health,disaster response,commercial promotion,and many other applications,but also give birth to threats that jeopardize each individual’s privacy and ***,most existing works in publishing social graph embedding data only focus on preserving social graph structure with less attention paid to the privacy issues inherited from social *** be specific,attackers can infer the presence of a sensitive relationship between two individuals by training a predictive model with the exposed social network *** this paper,we propose a novel link-privacy preserved graph embedding framework using adversarial learning,which can reduce adversary’s prediction accuracy on sensitive links while persevering sufficient non-sensitive information such as graph topology and node attributes in graph *** experiments are conducted to evaluate the proposed framework using ground truth social network datasets.

关键词： social network graph embedding privacy preservation adversarial learning

来源：评论

学校读者我要写书评

暂无评论

Predecessor Rain Events in the Yangtze River Delta Region Associated with South China Sea and Northwest Pacific Ocean(SCS-WNPO)Tropical Cyclones

引用

Advances in Atmospheric sciences 2023年第6期40卷 1021-1042页

作者： Huiyan XU Xiaofan LI Jinfang YIN Dengrong ZHANG Zhejiang Provincial Key Laboratory of Urban Wetlands and Regional Change School of Information Science and TechnologyHangzhou Normal UniversityHangzhou 311121China Key Laboratory of Geoscience Big Data and Deep Resource of Zhejiang Province School of Earth SciencesZhejiang UniversityHangzhou 310027China State Key Laboratory of Severe Weather(LaSW) Chinese Academy of Meteorological Sciences(CAMS)Beijing 100081China

Predecessor rain events(PREs) in the Yangtze River Delta(YRD) region associated with the South China Sea and Northwest Pacific Ocean(SCS-WNPO) tropical cyclones(TCs) are investigated during the period from 2010 to *** indicate that approximately 10% of TCs making landfall in China produce PREs over the YRD region;however,they are seldom forecasted. PREs often occur over the YRD region when TCs begin to be active in the SCS-WNPO with westward paths, whilst the cold air is still existing or beginning to be present. PREs are more likely to peak in June and September. The distances between the PRE centers and the parent TC range from 900 to 1700 km. The median value of rain amounts and the median lifetime of PREs is approximately 200 mm and 24 h, respectively. Composite results suggest that PREs form in the equatorward jet-entrance region of the upper-level westerly jet(WJ), where a 925-hPa equivalent potential temperature ridge is located east of a 500-hPa trough. Deep moisture is transported from the TC vicinity to the remote PREs region. The ascent of this deep moist air in front of the 500-hPa trough and frontogenesis beneath the equatorward entrance region of the WJ is advantageous for the occurrence of PREs in the YRD region. The upper-level WJ may be affected by the subtropical high and westerly trough in the Northwest Pacific Ocean, and the occurrence of PREs may favor the maintenance of the upper-level WJ. The upper-level outflow of TCs in the SCS plays a secondary role.

关键词： tropical cyclone heavy rain westerly trough upper-level jet stream

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：