检索结果-内蒙古大学图书馆

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Tong-Jun Li Run-Ze Zhang School of Information Engineering Zhejiang Ocean University Zhoushan Zhejiang China Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province China

Formal concept analysis is a key tool in data analysis and knowledge representation and a specific method for granular computing. Object granules constitute the basic granular knowledge in a concept lattice. Three-way decision is a reasonable approach to extracting decision rules. This study employs the principle of three-way decision to divide all the object granules of a formal context into three parts: positive, negative and boundary regions, then two groups of certainty decision rules are extracted from the positive region and the negative region, and one group of possibility decision rules is induced from the boundary region. The notion of attribute reduction keeping the performance of the decision rules unchanged are proposed. An approach for computing attribute reducts is put forward by utilizing the discernibility matrix and discernibility function. Some examples are taken to explain or show the relevant conclusions and prove the feasibility of the reduction method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Few-shot Open Relation Extraction with Gaussian Prototype and Adaptive Margin

arXiv

引用

arXiv 2024年

作者： Guo, Tianlin Zhang, Lingling Wang, Jiaxin Lei, Yunkuo Li, Yifei Wang, Haofen Liu, Jun School of Computer Science and Technology Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi'an Jiaotong University Xi’an710049 China School of Computer Science and Technology Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi’an710049 China College of Design and Innovation Tongji University Shanghai200092 China

Few-shot relation extraction with none-of-the-above (FsRE with NOTA) aims at predicting labels in few-shot scenarios with unknown classes. FsRE with NOTA is more challenging than the conventional few-shot relation extraction task, since the boundaries of unknown classes are complex and difficult to learn. Meta-learning based methods, especially prototype-based methods, are the mainstream solutions to this task. They obtain the classification boundary by learning the sample distribution of each class. However, their performance is limited because few-shot overfitting and NOTA boundary confusion lead to misclassification between known and unknown classes. To this end, we propose a novel framework based on Gaussian prototype and adaptive margin named GPAM for FsRE with NOTA, which includes three modules, semi-factual representation, GMM-prototype metric learning and decision boundary learning. The first two modules obtain better representations to solve the few-shot problem through debiased information enhancement and Gaussian space distance measurement. The third module learns more accurate classification boundaries and prototypes through adaptive margin and negative sampling. In the training procedure of GPAM, we use contrastive learning loss to comprehensively consider the effects of range and margin on the classification of known and unknown classes to ensure the model's stability and robustness. Sufficient experiments and ablations on the FewRel dataset show that GPAM surpasses previous prototype methods and achieves state-of-the-art performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Label Enhanced Event Detection with Collective knowledge and Heterogeneous Graph

Label Enhanced Event Detection with Collective Knowledge and...

引用

IEEE International Conference on big knowledge (ICBK)

作者： Gongqing Wu Zhenya Lu Zhuochun Miao Xingrui Zhuo Zan Zhang Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei University of Technology Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei China

Event Detection (ED) aims to recognize instances of specified types of event triggers in text. Existing graph neural network-based models have achieved promising progress to alleviate this problem by capturing different orders of syntactic information, but they are limited by two issues. First, the long-range syntactic information between words is not fully exploited. Second, they ignore the semantic information provided by dependency labels which provide linguistic knowledge that is useful to ED. As a result, we proposed a label-enhanced dense graph convolutional network that employs dense connectivity and Graph Transformer Networks (GTN) to learn a flexible selection of edge types and composite relations between the words. Each layer can make use of the collective knowledge of dense blocks in order to model syntactic dependencies over long distances through dense connectivity. The proposed model achieves state-of-the-art performance for ED on common datasets after extensive experiments are conducted to show its advantages.

关键词： knowledge engineering Event detection Text recognition Semantics Syntactics Linguistics Transformers

来源：评论

学校读者我要写书评

暂无评论

K-ON: Stacking knowledge On the Head Layer of Large Language Model

arXiv

引用

arXiv 2025年

作者： Guo, Lingbing Zhang, Yichi Bo, Zhongpu Chen, Zhuo Sun, Mengshu Zhang, Zhiqiang Zhang, Wen Chen, Huajun College of Computer Science and Technology Zhejiang University China ZJU-Ant Group Joint Lab of Knowledge Graph China Ant Group China School of Software Technology Zhejiang University China Zhejiang Key Laboratory of Big Data Intelligent Computing China

Recent advancements in large language models (LLMs) have significantly improved various natural language processing (NLP) tasks. Typically, LLMs are trained to predict the next token, aligning well with many NLP tasks. However, in knowledge graph (KG) scenarios, entities are the fundamental units and identifying an entity requires at least several tokens. This leads to a granularity mismatch between KGs and natural languages. To address this issue, we propose K-ON, which integrates KG knowledge into the LLM by employing multiple head layers for next k-step prediction. K-ON can not only generate entity-level results in one step, but also enables contrastive loss against entities, which is the most powerful tool in KG representation learning. Experimental results show that K-ON outperforms state-of-the-art methods that incorporate text and even the other modalities. Copyright © 2025, The Authors. All rights reserved.

关键词： knowledge graph

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

Deep Semantic-Enhanced Event Detection via Symmetric Graph Convolutional Network

Deep Semantic-Enhanced Event Detection via Symmetric Graph C...

引用

IEEE International Conference on big knowledge (ICBK)

作者： Chenchen Sun Xingrui Zhuo Zhenya Lu Chenyang Bu Gongqing Wu Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei University of Technology Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei China

Event detection, an important research topic of information extraction, aims to automatically identify and classify event instances from the text. Previous studies have introduced methods combining syntactic information and graph convolutional networks into the field of event detection and verified their effectiveness. However, such methods often ignore the high-order information on the syntactic tree with noisy words, which limits their classification quality. In this paper, we propose a deep symmetric graph convolutional network to organically integrate high-order and low-order syntactic information to strengthen the semantic features of sentences. Specifically, we design a skip connection with attention gating mechanism, which selects valuable low-order syntactic information under the supervision of high-order syntactic information to strengthen the aggregation of high-order and low-order syntactic information. Then, a graph perturbation mechanism is proposed to discard noisy nodes on the syntactic graph to reduce the noisy information in the high-order syntactic information. We conducted extensive experiments on the widely used ACE 2005 benchmark, and the experimental results demonstrate that our method significantly outperforms state-of-the-art methods. Then, a graph perturbation mechanism is proposed to discard noisy nodes on the syntactic graph to reduce the noisy information in the high-order syntactic information. We conducted extensive experiments on the widely used ACE 2005 benchmark, and the experimental results demonstrate that our method significantly outperforms state-of-the-art methods. We conducted extensive experiments on the widely used ACE 2005 benchmark, and the experimental results demonstrate that our method significantly outperforms state-of-the-art methods. Then, a graph perturbation mechanism is proposed to discard noisy nodes on the syntactic graph to reduce the noisy information in the high-order syntactic information.

关键词： knowledge engineering Event detection Perturbation methods Semantics Syntactics Benchmark testing Information retrieval

来源：评论

学校读者我要写书评

暂无评论

A-Map: Interactive Visual Exploration of Intercity Accessibility Dynamics Based on Railway Network data

A-Map: Interactive Visual Exploration of Intercity Accessibi...

引用

Pacific (formerly Asia-Pacific APVIS) Visualization Symposium

作者： Kaichen Nie Hanning Shao Yuchu Luo Min Tian Hao Wu Wei Zeng Xin Fu Xiaoru Yuan Key Laboratory of Machine Perception (Ministry of Education) School of AI Peking University Hong Kong University of Science and Technology Guangzhou Chang’an University National Engineering Laboratory for Big Data Analysis and Application Peking University

ISBN: (数字)9798350393804

ISBN: (纸本)9798350393811

Railway transportation is closely linked to everyday lives while also aiding domain experts in analyzing national or regional development. However, discrepancies between travel time reduced by railways and actual distance pose challenges in visualizing the accessibility. Existing methods either struggle to simultaneously depict the accessibility relationships among all cities or disregard genuine geographical positions, leading to spatial cognitive confusion. In this work, we propose a novel approach to balance between the geographical positions and travel time between cities. We construct linear cartograms to represent accessibility while preserving better local railway network structures compared with existing methods. We further propose the A-Map system, enabling users to interactively explore the extensive development of China’s railway system over decades. We validate the effectiveness of our proposed layout algorithm from qualitative metric evaluation and illustrate the applicability of our system with results.

关键词： Measurement Visualization Heuristic algorithms Urban areas Layout Transportation data visualization

来源：评论

学校读者我要写书评

暂无评论

Tokenization, Fusion, and Augmentation: Towards Fine-grained Multi-modal Entity Representation 39

Tokenization, Fusion, and Augmentation: Towards Fine-grained...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Yichi Chen, Zhuo Guo, Lingbing Xu, Yajing Hu, Binbin Liu, Ziqi Zhang, Wen Chen, Huajun College of Computer Science and Technology Zhejiang University China ZJU-Ant Group Joint Lab of Knowledge Graph China Ant Group China School of Software Technology Zhejiang University China Zhejiang Key Laboratory of Big Data Intelligent Computing China

ISBN: (纸本)157735897X

Multi-modal knowledge graph completion (MMKGC) aims to discover unobserved knowledge from given knowledge graphs, collaboratively leveraging structural information from the triples and multi-modal information of the entities to overcome the inherent incompleteness. Existing MMKGC methods usually extract multi-modal features with pre-trained models, resulting in coarse handling of multi-modal entity information, overlooking the nuanced, fine-grained semantic details and their complex interactions. To tackle this shortfall, we introduce a novel framework MYGO to tokenize, fuse, and augment the fine-grained multi-modal representations of entities and enhance the MMKGC performance. Motivated by the tokenization technology, MYGO tokenizes multi-modal entity information as fine-grained discrete tokens and learns entity representations with a cross-modal entity encoder. To further augment the multi-modal representations, MYGO incorporates fine-grained contrastive learning to highlight the specificity of the entity representations. Experiments on standard MMKGC benchmarks reveal that our method surpasses 19 of the latest models, underlining its superior performance. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Low-rank matrix recovery with total generalized variation for defending adversarial examples

引用

Frontiers of Information Technology & Electronic engineering 2024年第3期25卷 432-445页

作者： Wen LI Hengyou WANG Lianzhi HUO Qiang HE Linlin CHEN Zhiquan HE Wing W.Y.Ng School of Science Beijing University of Civil Engineering and ArchitectureBeijing 100044China School of Computer Science and Engineering South China University of TechnologyGuangzhou 510006China Aerospace Information Research Institute Chinese Academy of SciencesBeijing 100094China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen 518060China Institute of Big Data Modeling and Technology Beijing University of Civil Engineering and ArchitectureBeijing 100044China

Low-rank matrix decomposition with first-order total variation(TV)regularization exhibits excellent performance in exploration of image *** advantage of its excellent performance in image denoising,we apply it to improve the robustness of deep neural ***,although TV regularization can improve the robustness of the model,it reduces the accuracy of normal samples due to its *** our work,we develop a new low-rank matrix recovery model,called LRTGV,which incorporates total generalized variation(TGV)regularization into the reweighted low-rank matrix recovery *** the proposed model,TGV is used to better reconstruct texture information without *** reweighted nuclear norm and Li-norm can enhance the global structure ***,the proposed LRTGV can destroy the structure of adversarial noise while re-enhancing the global structure and local texture of the *** solve the challenging optimal model issue,we propose an algorithm based on the alternating direction method of *** results show that the proposed algorithm has a certain defense capability against black-box attacks,and outperforms state-of-the-art low-rank matrix recovery methods in image restoration.

关键词： Total generalized variation Low-rank matrix Alternating direction method of multipliers Adversarial example

来源：评论

学校读者我要写书评

暂无评论

FrustumFusionNets: A Three-Dimensional Object Detection Network Based on Tractor Road Scene

arXiv

引用

arXiv 2025年

作者： Yang, Lili Chang, Mengshuai Guo, Xiao Feng, Yuxin Mei, Yiwen Wu, Caicong College of Information and Electrical Engineering China Agricultural University Beijing100083 China Key Laboratory of Agricultural Machinery Monitoring and Big Data Applications Ministry of Agriculture and Rural Affairs Beijing100083 China

To address the issues of the existing frustum-based methods' underutilization of image information in road three-dimensional object detection as well as the lack of research on agricultural scenes, we constructed an object detection dataset using an 80-line Light Detection And Ranging (LiDAR) and a camera in a complex tractor road scene and proposed a new network called FrustumFusionNets (FFNets). Initially, we utilize the results of image-based two-dimensional object detection to narrow down the search region in the three-dimensional space of the point cloud. Next, we introduce a Gaussian mask to enhance the point cloud information. Then, we extract the features from the frustum point cloud and the crop image using the point cloud feature extraction pipeline and the image feature extraction pipeline, respectively. Finally, we concatenate and fuse the data features from both modalities to achieve three-dimensional object detection. Experiments demonstrate that on the constructed test set of tractor road data, the FrustumFusionNetv2 achieves 82.28% and 95.68% accuracy in the three-dimensional object detection of the two main road objects, cars and people, respectively. This performance is 1.83% and 2.33% better than the original model. It offers a hybrid fusion-based multi-object, high-precision, real-time three-dimensional object detection technique for unmanned agricultural machines in tractor road scenarios. On the Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) Benchmark Suite validation set, the FrustumFusionNetv2 also demonstrates significant superiority in detecting road pedestrian objects compared with other frustum-based three-dimensional object detection methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Tractors (truck)

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：