检索结果-内蒙古大学图书馆

31st International Conference on Computational Linguistics, COLING 2025

作者： Zhang, Fu Liu, He Li, Zehan Cheng, Jingwei School of Computer Science and Engineering Northeastern University China Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education Northeastern University China

ISBN: (纸本)9798891761964

Zero-shot Relation Extraction (ZSRE) aims to predict novel relations from sentences with given entity pairs, where the relations have not been encountered during training. Prototype-based methods, which achieve ZSRE by aligning the sentence representation and the relation prototype representation, have shown great potential. However, most existing works focus solely on improving the quality of prototype representations, neglecting sentence representations, and lacking interaction between different types of relation side information. In this paper, we propose a novel ZSRE framework named CE-DA, which includes two modules: Custom Embedding and Dynamic Aggregation. We employ a two-stage approach to obtain customized embeddings of sentences. In the first stage, we train a sentence encoder through unsupervised contrastive learning, and in the second stage, we highlight the potential relations between entities in sentences using carefully designed entity emphasis prompts to further enhance sentence representations. Additionally, our dynamic aggregation method assigns different weights to different types of relation side information through a learnable network to enhance the quality of relation prototype representations. In contrast to traditional methods that treat the importance of all side information equally, our dynamic aggregation method further strengthens the interaction between different types of relation side information. Our method demonstrates competitive performance across various metrics on two ZSRE datasets. © 2025 Association for Computational Linguistics.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Inductive Link Prediction in N-ary Knowledge Graphs 31

Inductive Link Prediction in N-ary Knowledge Graphs

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Wei, Jiyao Guan, Saiping Jin, Xiaolong Guo, Jiafeng Cheng, Xueqi School of Computer Science and Technology University of Chinese Academy of Sciences Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China

ISBN: (纸本)9798891761964

N-ary Knowledge Graphs (NKGs), where a fact can involve more than two entities, have gained increasing attention. Link Prediction in NKGs (LPN) aims to predict missing elements in facts to facilitate the completion of NKGs. Current LPN methods implicitly operate under a closed-world assumption, meaning that the sets of entities and roles are fixed. These methods focus on predicting missing elements within facts composed of entities and roles seen during training. However, in reality, new facts involving unseen entities and roles frequently emerge, requiring completing these facts. Thus, this paper proposes a new task, Inductive Link Prediction in NKGs (ILPN), which aims to predict missing elements in facts involving unseen entities and roles in emerging NKGs. To address this task, we propose a Meta-learning-based Nary knowledge Inductive Reasoner (MetaNIR), which employs a graph neural network with meta-learning mechanisms to embed unseen entities and roles adaptively. The obtained embeddings are used to predict missing elements in facts involving unseen elements. Since no existing dataset supports this task, three datasets are constructed to evaluate the effectiveness of MetaNIR. Extensive experimental results demonstrate that MetaNIR consistently outperforms representative models across all datasets. © 2025 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

Hamiltonian boundary value methods applied to KdV-KdV systems

引用

Applied Numerical Mathematics 2025年 214卷 1-27页

作者： Luo, Qian Xiao, Aiguo Luo, Xuqiong Yan, Xiaoqiang School of Mathematics and Computational Science Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan University Hunan 411105 China Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Hunan 411105 China School of Mathematics and Statistics Changsha University of Science and Technology Changsha410114 China National Center for Applied Mathematics in Hunan Xiangtan University Hunan 411105 China

In this paper, we propose a highly accurate scheme for two KdV systems of the Boussinesq type under periodic boundary conditions. The proposed scheme combines the Fourier-Galerkin method for spatial discretization with Hamiltonian boundary value methods for time integration, ensuring the conservation of discrete mass and energy. By expanding the system in Fourier series, the equations are firstly transformed into Hamiltonian form, preserving the original Hamiltonian structure. Applying the Fourier-Galerkin method for semi-discretization in space, we obtain a large-scale system of Hamiltonian ordinary differential equations, which is then solved using a class of energy-conserving Runge-Kutta methods, known as Hamiltonian boundary value methods. The efficiency of this approach is assessed, and several numerical examples are provided to demonstrate the effectiveness of the method. © 2025 IMACS

关键词： Ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

Learning Without Forgetting for Vision-Language Models

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第6期47卷 4489-4504页

作者： Zhou, Da-Wei Zhang, Yuanhan Wang, Yan Ning, Jingyi Ye, Han-Jia Zhan, De-Chuan Liu, Ziwei Nanjing University School of Artificial Intelligence China Nanjing University National Key Laboratory for Novel Software Technology Nanjing210023 China Nanyang Technological University S-Lab College of Computing and Data Science 639798 Singapore

Class-Incremental Learning (CIL) or continual learning is a desired capability in the real world, which requires a learning system to adapt to new tasks without forgetting former ones. While traditional CIL methods focus on visual information to grasp core features, recent advances in Vision-Language Models (VLM) have shown promising capabilities in learning generalizable representations with the aid of textual information. However, when continually trained with new classes, VLMs often suffer from catastrophic forgetting of former knowledge. Applying VLMs to CIL poses two major challenges: 1) how to adapt the model without forgetting;and 2) how to make full use of the multi-modal information. To this end, we propose PROjectiOn Fusion (Proof) that enables VLMs to learn without forgetting. To handle the first challenge, we propose training task-specific projections based on the frozen image/text encoders. When facing new tasks, new projections are expanded, and former projections are fixed, alleviating the forgetting of old concepts. For the second challenge, we propose the fusion module to better utilize the cross-modality information. By jointly adjusting visual and textual features, the model can capture better task-specific semantic information that facilitates recognition. Extensive experiments on nine benchmark datasets with various continual learning scenarios and various VLMs validate that Proofachieves state-of-the-art performance. Code is available at https://***/zhoudw-zdw/PROOF. © 1979-2012 IEEE.

关键词： Visualization Tuning Adaptation Models Training Transformers Predictive Models Continuing Education Software Resists Learning Systems Class Incremental Learning Vision Language Model Continual Learning Catastrophic Forgetting Vision Language Models Visual Information Visual Features Benchmark datasets Textual Information Incremental Learning Textual Features Catastrophic Forgetting Recent Advances In Models Fine Tuned Learning Process Contextual Information Latent Space Joint Space Linear Layer Subsequent Task Self Attention Mechanism Training Instances Pre Trained Weights TV Series Projection Layer Image Encoder Unseen Classes Pre Trained Encoder Domain Gap Text Encoder Vision Transformer Tuning Techniques

来源：评论

学校读者我要写书评

暂无评论

Controlled-source electromagnetic noise attenuation via a deep convolutional neural network and high-quality sounding curve screening mechanism

引用

Geophysics 2025年第3期90卷 WA125-WA140页

作者： Liu, Yecheng Li, Diquan Li, Jin Zhang, Xian Central South University Monitoring Ministry of Education Key Laboratory of Metallogenic Prediction of Nonferrous Metals and Geological Environment Changsha China Hunan Provincial Key Laboratory of Non-ferrous Resources and Geological Hazard Detection Changsha China Central South University School of Geoscience and Info-physics Changsha China Hunan Normal University College of Information Science and Engineering Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Changsha China Hunan University of Finance and Economics School of Information Technology and Management Hunan Provincial Key Laboratory of Finance & Economics Big Data Science and Technology Changsha China

Strong noise is one of the biggest challenges in controlled-source electromagnetic (CSEM) exploration, which severely affects the quality of the recorded signal. We develop a novel and effective CSEM noise attenuation method that integrates a deep convolutional neural network (DCNN) with a high-quality sounding curve screening mechanism. This method first uses a DCNN to learn the large-scale noise characteristics of CSEM measured data and build a DCNN denoising model for attenuating the noise. Because some impulse noise remains after DCNN denoising, the high-quality sounding curve screening mechanism is innovatively applied to optimize the DCNN denoised data. The core of this method is the smoothness value (SV), which quantitatively evaluates the smoothness of the sounding curve (apparent resistivity curve). In effect, the mechanism segments the overall DCNN denoised data and calculates the corresponding sounding curve and its SV for each segment. The highest-quality sounding curve can be screened out by comparing the SVs of all curves as well as obtaining the highest-quality data segment present in the overall DCNN denoised data. Finally, our method is validated with synthetic and field data, demonstrating its feasibility and effectiveness in attenuating large-scale CSEM noise. The quality of CSEM data, which is heavily affected by noise, is significantly improved after processing by our method. © 2025 Society of Exploration Geophysicists. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Large Language Model-Based Event Relation Extraction with Rationales 31

Large Language Model-Based Event Relation Extraction with Ra...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Hu, Zhilei Li, Zixuan Jin, Xiaolong Bai, Long Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of SciencesSchool of Computer Science and Technology University of Chinese Academy of Sciences

ISBN: (纸本)9798891761964

Event Relation Extraction (ERE) aims to extract various types of relations between different events within texts. Although Large Language Models (LLMs) have demonstrated impressive capabilities in many natural language processing tasks, existing ERE methods based on LLMs still face three key challenges: (1) Time Inefficiency: The existing pairwise method of combining events and determining their relations is time-consuming for LLMs. (2) Low Coverage: When dealing with numerous events in a document, the limited generation length of fine-tuned LLMs restricts the coverage of their extraction results. (3) Lack of Rationale: Essential rationales concerning the results that could enhance the reasoning ability of the model are overlooked. To address these challenges, we propose LLMERE, an LLM-based approach with rationales for the ERE task. LLMERE transforms ERE into a question-and-answer task that may have multiple answers. By extracting all events related to a specified event at once, LLMERE reduces time complexity from O(n2) to O(n), compared to the pairwise method. Subsequently, LLMERE enhances the coverage of extraction results by employing a partitioning strategy that highlights only a portion of the events in the document at a time. In addition to the extracted results, LLMERE is also required to generate corresponding rationales/reasons behind them, in terms of event coreference information or transitive chains of event relations. Experimental results on three widely used datasets show that LLMERE achieves significant improvements over baseline methods. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

A HIGH ORDER SCHEME FOR FRACTIONAL DIFFERENTIAL EQUATIONS WITH THE CAPUTO-HADAMARD DERIVATIVE

引用

Journal of Computational Mathematics 2025年第3期43卷 615-640页

作者： Xingyang Ye Junying Cao Chuanju Xu School of Science Jimei UniversityXiamen 361021China School of Data Science and Information Engineering Guizhou Minzu UniversityGuiyang 550025China School of Mathematical Sciences and Fujian Provincial Key Laboratory of Mathematical Modeling and High Performance Scientific Computing Xiamen UniversityXiamen 361005China

In this paper,we consider numerical solutions of the fractional diffusion equation with theαorder time fractional derivative defined in the Caputo-Hadamard sense.A high order time-stepping scheme is constructed,analyzed,and numerically *** contribution of the paper is twofold:1)regularity of the solution to the underlying equation is investigated,2)a rigorous stability and convergence analysis for the proposed scheme is performed,which shows that the proposed scheme is 3+αorder *** numerical examples are provided to verify the theoretical statement.

关键词： Caputo-Hadamard derivative Fractional differential equations High order scheme Stability and convergence analysis

来源：评论

学校读者我要写书评

暂无评论

Laplacian Sparse Dynamic Slow Feature Analysis for Process Monitoring and Fault Isolation

引用

IEEE Sensors Journal 2025年第9期25卷 15653-15667页

作者： Wu, Ping Xue, Yikai Ni, Yuxuan Pan, Haipeng Zhang, Xi He, Yuchen Gao, Jinfeng Zhejiang Sci-Tech University School of Information Science and Engineering Hangzhou310018 China China Jiliang University Key Laboratory of Intelligent Manufacturing Quality Big Data Tracing and Analysis of Zhejiang Province Hangzhou314423 China

The process monitoring and fault isolation are essential for ensuring operational safety and maintaining product quality in the industrial processes. This study introduces a novel approach to process monitoring and fault isolation based on the Laplacian sparse dynamic slow feature analysis (LSDSFA). To simultaneously account for sparsity, dynamics, and global structural information, a new optimization framework for LSDSFA is proposed. This framework incorporates the n l1 norm and a Laplacian graph into dynamic slow feature analysis (SFA), with enhancements to process variable representation. The optimization problem is addressed using the alternating direction method of multipliers (ADMMs). The proposed method decomposes the process variable space into latent and residual subspaces. In addition, three monitoring statistics are developed to facilitate effective process monitoring, while fault isolation is achieved through a two-level contribution plot. Specifically, the intrinsic structure of the process data is captured by employing a graph Laplacian operator to explore intervariable correlations. Simultaneously, the incorporation of the graph Laplacian operator and l1 norm into dynamic SFA (DSFA) reduces variable redundancy, thereby exploiting the intrinsic structure of the process data more effectively and improving interpretability through the sparsity. Experimental evaluations conducted on the widely adopted Tennessee Eastman Process (TEP) benchmark and a real-world blast furnace ironmaking process (BFIP) demonstrate the superior performance of the proposed LSDSFA-based method in comparison with related techniques. © 2001-2012 IEEE.

关键词： Blast furnaces

来源：评论

学校读者我要写书评

暂无评论

MMH-FE:AMulti-Precision and Multi-Sourced Heterogeneous Privacy-Preserving Neural Network Training Based on Functional Encryption

引用

Computers, Materials & Continua 2025年第3期82卷 5387-5405页

作者： Hao Li Kuan Shao Xin Wang Mufeng Wang Zhenyong Zhang The State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang550025China Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science CenterQilu University of Technology(Shandong Academy of Sciences)Jinan250014China China Industrial Control Systems Cyber Emergency Response Team Beijing100040China

Due to the development of cloud computing and machine learning,users can upload their data to the cloud for machine learning model ***,dishonest clouds may infer user data,resulting in user data *** schemes have achieved secure outsourced computing,but they suffer from low computational accuracy,difficult-to-handle heterogeneous distribution of data from multiple sources,and high computational cost,which result in extremely poor user experience and expensive cloud computing *** address the above problems,we propose amulti-precision,multi-sourced,andmulti-key outsourcing neural network training ***,we design a multi-precision functional encryption computation based on Euclidean ***,we design the outsourcing model training algorithm based on a multi-precision functional encryption with multi-sourced ***,we conduct experiments on three *** results indicate that our framework achieves an accuracy improvement of 6%to 30%.Additionally,it offers a memory space optimization of 1.0×2^(24) times compared to the previous best approach.

关键词： Functional encryption multi-sourced heterogeneous data privacy preservation neural networks

来源：评论

学校读者我要写书评

暂无评论

DCT-DiffPose: A Lightweight Diffusion Model with Multi-Hypothesis for 3D Human Pose Estimation

引用

IEEE Access 2025年 13卷 73319-73331页

作者： Zhong, Linzhan Chen, Fangni Zheng, Bolun Feng, Rui Zhang, Lei Wan, Jian Zhejiang University of Science and Technology The College of Information and Electronic Engineering Hangzhou310023 China The Zhejiang Key Laboratory of Biomedical Intelligent Computing Technology Hangzhou310023 China Hangzhou Dianzi University School of Automation Hangzhou310018 China

3D human pose estimation is a crucial task in computer vision with extensive applications, yet it remains challenging due to depth ambiguity and constraints on computational efficiency. In this paper, we propose DCT-DiffPose, a novel framework that integrates a diffusion model with Confidence and Consistency-based Multi-Hypothesis Aggregation (CCMA). Moreover, it incorporate the Discrete Cosine Transform (DCT) for frequency-domain feature extraction. Specifically, the diffusion model generates diverse and plausible hypotheses, and CCMA aggregates them based on confidence and consistency, effectively addressing depth ambiguity. Additionally, we incorporate DCT into the self-attention mechanism to transform input data into the frequency domain, thereby enhancing feature extraction while significantly reducing computational complexity. To validate DCT-DiffPose, we conducted extensive experiments on the Human3.6M and MPI-INF-3DHP datasets. Our method achieves a 19% lower Mean Per Joint Position Error (MPJPE) and a 55% reduction in FLOPs compared to D3DP. The results demonstrate its excellent trade-off between accuracy and complexity. © 2013 IEEE.

关键词： Discrete cosine transforms

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：