检索结果-内蒙古大学图书馆

A Graph Attribute Aggregation Method based on Feature engineering

Journal of The Institution of Engineers (India): Series B 2022年第3期103卷 711-719页

作者： Wang, Hao Dong, Li-Yan Ma, Xin-Tao Sun, Ming-Hui College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China

In the fields of social network analysis and knowledge graph, many semi-supervised learning algorithms based on graph convolutional neural network (GCN) have been widely used. Most of these algorithms usually improve the structure of the neural network and the sampling method of each layer of the neural network. However, they don’t pay much attention to the data pre-processing of the algorithm. In the analysis of the input data, the words of different quality in these original data are unevenly distributed. This may obscure some useful data and highlight some irrelevant data. In order to verify the correctness of this hypothesis, the paper proposes a feature matrix compression algorithm (FMC algorithm) for data pre-processing of GCN-based algorithms. The algorithm analyzes and arranges the word columns of the input matrix (the feature of graph) according to the frequency of the word, then merges those words in which the word frequency is smaller, so as to emphasize the role of these words in the graph and optimize the data scale. The present work uses four mainstream datasets in the field and several representative and different algorithms to complete the experiment. The experimental results show that the FMC algorithm achieves better performance. © 2021, The Institution of Engineers (India).

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Confidence-aware Contrastive Learning for Selective Classification 41

Confidence-aware Contrastive Learning for Selective Classifi...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wu, Yu-Chang Lyu, Shen-Huan Shang, Haopu Wang, Xiangyu Qian, Chao National Key Laboratory for Novel Software Technology Nanjing University China School of Artificial Intelligence Nanjing University China Key Laboratory of Water Big Data Technology Ministry of Water Resources Hohai University China College of Computer Science and Software Engineering Hohai University China

Selective classification enables models to make predictions only when they are sufficiently confident, aiming to enhance safety and reliability, which is important in high-stakes scenarios. Previous methods mainly use deep neural networks and focus on modifying the architecture of classification layers to enable the model to estimate the confidence of its prediction. This work provides a generalization bound for selective classification, disclosing that optimizing feature layers helps improve the performance of selective classification. Inspired by this theory, we propose to explicitly improve the selective classification model at the feature level for the first time, leading to a novel Confidence-aware Contrastive Learning method for Selective Classification, CCL-SC, which similarizes the features of homogeneous instances and differentiates the features of heterogeneous instances, with the strength controlled by the model's confidence. The experimental results on typical datasets, i.e., CIFAR-10, CIFAR-100, CelebA, and ImageNet, show that CCL-SC achieves significantly lower selective risk than state-of-the-art methods, across almost all coverage degrees. Moreover, it can be combined with existing methods to bring further improvement. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Learning Inter-Entity Interaction for Few-Shot knowledge Graph Completion

Learning Inter-Entity Interaction for Few-Shot Knowledge Gra...

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Li, Yuling Yu, Kui Huang, Xiaoling Zhang, Yuhong Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei China School of Computer Science and Information Enginerring Hefei University of Technology China

Few-shot knowledge graph completion (FKGC) aims to infer unknown fact triples of a relation using its few-shot reference entity pairs. Recent FKGC studies focus on learning semantic representations of entity pairs by separately encoding the neighborhoods of head and tail entities. Such practice, however, ignores the inter-entity interaction, resulting in low-discrimination representations for entity pairs, especially when these entity pairs are associated with 1-to-N, N-to-1, and N-to-N relations. To address this issue, this paper proposes a novel FKGC model, named Cross-Interaction Attention Network (CIAN) to investigate the inter-entity interaction between head and tail entities. Specifically, we first explore the interactions within entities by computing the attention between the task relation and each entity neighbor, and then model the interactions between head and tail entities by letting an entity to attend to the neighborhood of its paired entity. In this way, CIAN can figure out the relevant semantics between head and tail entities, thereby generating more discriminative representations for entity pairs. Extensive experiments on two public datasets show that CIAN outperforms several state-of-the-art methods. The source code is available at https://***/cjlyl/FKGC-CIAN. © 2022 Association for Computational Linguistics.

关键词： knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Pan-media liquid metal 3D printing

引用

The Innovation 2025年第4期6卷 7-8页

作者： Xiaohui Shan Weichen Feng Minghui Guo Xuelin Wang Jing Liu School of Biomedical Engineering Tsinghua UniversityBeijing 100084China Key Laboratory of Cryogenic Science and Technology Technical Institute of Physics and ChemistryChinese Academy of SciencesBeijing 100190China Beijing Advanced Innovation Center for Biomedical Engineering Beijing Advanced Innovation Center for Big Data-Based Precision MedicineSchool of Engineering MedicineBeihang UniversityBeijing 100191China

INTRODUCTION The manufacturing industry has evolved from traditional forging and cutting to three-dimensional(3D)printing,a revolutionary technology that expands human imagination by creating everything of complex shapes and intricate structures,making it a cornerstone of smart manufacturing.1 However,conventional fabrications may encounter bottlenecks that seriously restrict their printing across different inks,ambient,and *** existing 3D printing methods to produce target functional components on diverse working media,therefore,requires significant *** highly adaptable 3D printing inks,liquid metals(LMs)open large spaces to address such challenges due to their versatile capabilities,such as fluidities,conductivities,easy solid-liquid transitions,and *** continuous efforts are being increasingly made in LM printing in different media,2 there is still no generalized methodology or concept proposed to unite all LM 3D printing techniques,inks,and media *** achieve this intriguing target,here we present a unified 3D printing concept,termed pan-media liquid metal 3D printing,to manufacture customized end-user devices as ***-media 3D printing means that it is able to administrate printing with any ink and any working ambient,from gases and liquids to soft matters,bio-tissues,and rigid media,transcending the boundaries of traditional printing ***,with intentionally introduced physical or chemical processing between LM inks and ambient,pan-media LM 3D printing could achieve a much wider variety of 3D object and targeted functions over existing *** synthesizing the pan-media theory of LM 3D printing,we prospect a pan-media manufacturing center equipped with functional ink storage,media library,printing head system,and control units,all integrated to fully address the desired printing tasks.

关键词： expands human imagination Liquid metals creating everything complex shapes intricate forging cutting smart manufacturing d printing produce target functional com D printing

来源：评论

学校读者我要写书评

暂无评论

Multi-lingual acquisition on multimodal pre-training for cross-modal retrieval 22

Multi-lingual acquisition on multimodal pre-training for cro...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Liang Zhang Anwen Hu Qin Jin School of Information Renmin University of China School of Information Renmin University of China and Key Laboratory of Data Engineering and Knowledge Engineering (MOE) Renmin University of China

ISBN: (纸本)9781713871088

Vision and diverse languages are important information sources in our living world. A model that understands multi-modalities and multi-languages can be applied to a wider range of real-life scenarios. To build such a multimodal and multilingual model, existing works try to ensemble vision-language data from multiple languages in pre-training. However, due to the large number of languages, these works often require huge computing resources and cannot be flexibly extended to new languages. In this work, we propose a Multi-Lingual Acquisition (MLA) framework that can easily empower a monolingual Vision-Language Pre-training (VLP) model with multilingual capability. Specifically, we design a lightweight language acquisition encoder based on state-of-the-art monolingual VLP models. We further propose a two-stage training strategy to optimize the language acquisition encoder, namely the Native Language Transfer stage and the Language Exposure stage. With much less multilingual training data and computing resources, our model achieves state-of-the-art performance on multilingual image-text and video-text retrieval benchmarks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unlocking the Potential of Model Merging for Low-Resource Languages

Unlocking the Potential of Model Merging for Low-Resource La...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Tao, Mingxu Zhang, Chen Huang, Quzhe Ma, Tianyao Huang, Songfang Zhao, Dongyan Feng, Yansong Wangxuan Institute of Computer Technology Peking University China State Key Laboratory of General Artificial Intelligence Peking University China Center for Data Science Peking University China College of Engineering Peking University China

ISBN: (纸本)9798891761681

Adapting large language models (LLMs) to new languages typically involves continual pre-training (CT) followed by supervised finetuning (SFT).However, this CT-then-SFT approach struggles with limited data in the context of low-resource languages, failing to balance language modeling and task-solving *** thus propose a new model merging solution as an alternative for low-resource languages, combining models with distinct capabilities into a single model without additional *** use model merging to develop task-solving LLMs for low-resource languages without SFT data in the target *** experiments based on Llama-2-7B demonstrate that model merging effectively endows LLMs for low-resource languages with task-solving abilities, outperforming CT-then-SFT in scenarios with extremely scarce *** performance saturation in model merging with increasingly more training tokens, we further analyze the merging process and introduce a slack variable to the model merging algorithm to mitigate the loss of important parameters, thereby enhancing model *** hope that model merging can benefit more human languages suffering from data scarcity with its higher data efficiency. © 2024 Association for Computational Linguistics.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

A hybrid model of CNN+ViT of the recognition for Spodoptera frugiperda larval instar stages

A hybrid model of CNN+ViT of the recognition for Spodoptera ...

引用

2023 International Conference on Computer Application and Information Security, ICCAIS 2023

作者： Wang, Mingyang Lu, Ying Xu, Quanyuan Xiang, Tianzi Chang, Jumei Zhang, Hanrui College of Big Data and Intelligent Engineering Southwest Forestry University Yunnan Kunming650024 China Key Laboratory of Forestry and Ecological Big Data State Forestry Administration Southwest Forestry University Yunnan Kunming650024 China

ISBN: (纸本)9781510675032

Spodoptera frugiperda (Fall armyworm, FAW) is one of the major agricultural pests in the world. It is of great significance for ensuring crop yield to accurately recognize FAW larval instars. This research proposes a hybrid model of Convolutional Neural Network (CNN) and Vision Transformer (ViT) for the recognition of FAW larval instars. The model uses CNN to extract local features of larval images and ViT to capture global image dependencies, achieving effective recognition of larval instars. To verify the model proposed in this paper, an image dataset of 5,006 images balancing the larval instars which are from the 1st to the 6th of FAWs is established. The proposed model achieved recognition accuracy of 99.60% and 92.11% respectively in the two cases of using and not using pre-training. The results show that the proposed model achieves higher recognition accuracy than AlexNet, VGG16, ResNet50, ResNet101, and ViT-B. Moreover, it does not rely on pre-trained weights and performs well on relatively small datasets. The research in this paper provides a new technique of the recognition for FAW instars and also provides a reference for other agricultural pest image recognition tasks. © 2024 SPIE.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Optimizing Random Access to Hierarchically-Compressed data on GPU

Optimizing Random Access to Hierarchically-Compressed Data o...

引用

Supercomputing Conference

作者： Feng Zhang Yihua Hu Haipeng Ding Zhiming Yao Zhewei Wei Xiao Zhang Xiaoyong Du Key Laboratory of Data Engineering and Knowledge Engineering (MOE) School of Information Renmin University of China Beijing China

ISBN: (纸本)9781665454452

GPU's powerful computational capacity holds great potentials for processing hierarchically-compressed data without decompression in data science domain. Unfortunately, existing GPU approaches offer only traversal-based data analytics; random access is extremely inefficient, substantially limiting their utility. To solve this problem, we develop a novel and broadly applicable optimization that enables efficient random access to hierarchically-compressed data without decompression in GPU memory. We address three major challenges for enabling efficient random access to compressed data on GPUs. The first challenge is designing GPU data structures that support random access. The second challenge is efficiently generating data structures on GPU. Generating data structures for random access is costly on the CPU, and the inefficiency increases dramatically when PCIe data transmission is incorporated. The third challenge is query processing on compressed data in GPU memory. Random accesses, including data updates, result in significant conflicts between massive threads. To solve the first challenge, we propose and modify a number of compressed data structures, including indexing within the complicated GPU memory hierarchy. To address the second challenge, we develop a two-phase process for generating these data structures on the GPU. To handle the third challenge, we propose a double-parsing design to avoid data conflicts. We evaluate our solution on two GPU platforms using five real-world datasets. Experiments show that the random access operations on GPU can achieve 65.04x average speedup compared to the state-of-the-art method.

关键词： Limiting Query processing Instruction sets High performance computing Memory management Graphics processing units data science

来源：评论

学校读者我要写书评

暂无评论

CompressStreamDB: Fine-Grained Adaptive Stream Processing without Decompression

CompressStreamDB: Fine-Grained Adaptive Stream Processing wi...

引用

International Conference on data engineering

作者： Yu Zhang Feng Zhang Hourun Li Shuhao Zhang Xiaoyong Du Key Laboratory of Data Engineering and Knowledge Engineering (MOE) and School of Information Renmin University of China Information Systems Technology and Design Pillar Singapore University of Technology and Design

Stream processing prevails and SQL query on streams has become one of the most popular application scenarios. For example, in 2021, the global number of active IoT endpoints reaches 12.3 billion. Unfortunately, the increasing scale of data and strict user requests place much pressure on existing stream processing systems, requiring high processing throughput with low latency. To further improve the performance of current stream processing systems, we propose a compression-based stream processing engine, called CompressStreamDB, which enables adaptive fine-grained stream processing directly on compressed streams, without decompression. Particularly, CompressStreamDB involves eight compression methods targeting various data types in streams, and it also provides a cost model for dynamically selecting the appropriate compression methods. By exploring data redundancy among streams, CompressStreamDB not only saves space in data transmission between client and server, but also achieves high throughput with low latency in SQL query on stream processing. Our experimental results show that compared to the state-of-the-art stream processing system on uncompressed streams, CompressStreamDB achieves 3.24× throughput improvement and 66.0% lower latency on average. Besides, CompressStreamDB saves 66.8% space.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on optimal deep learning-based formation flight positioning of UAV

Research on optimal deep learning-based formation flight pos...

引用

作者： Lu, Jing Li, Yongyi Faculty of Science Beibu Gulf University Qinzhou China Qinzhou Key Laboratory of Big Data Resource Utilization College of Electronic and Information Engineering Beibu Gulf University Qinzhou China

The article examines the positional relationships and transmission/reception signal direction information within unmanned aerial vehicle (UAV) cluster formations. Considering the distinctive characteristics of various formation shapes (such as circle and cone), a study is conducted on the polar and Cartesian coordinate systems in neural network models to address position deviation issues arising in UAV formation flights. The passive receiving signal UAV positioning model is established by applying the triangular cosine theorem. Additionally, the position relationship model of the UAV is formulated using optimization theory. The article introduces a deep learning-based deviated UAV adjustment algorithm designed to automatically adjust UAV positions. This is achieved by establishing a triangular relationship between the passive signal receiving UAV and other UAVs. The implementation involves C# programming and MATLAB visualization. The proposed method not only resolves UAV positioning and position adjustment challenges but also optimizes the adjustment strategy. This optimization leads to maximum savings in time and distance costs associated with sending and receiving signals among UAVs, thereby enhancing the overall performance of UAVs during flights. © 2024 John Wiley & Sons Ltd.

关键词： Unmanned aerial vehicles (UAV)

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：