检索结果-内蒙古大学图书馆

12th National CCF Conference on Natural Language Processing and Chinese computing, NLPCC 2023

作者： Liu, Mengjuan Liu, Chenyang Yang, Yunfan Liu, Jiang Jing, Mohan Network and Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9783031446955

Recently, utilizing deep neural networks to build the open-domain dialogue models has become a hot topic. However, the responses generated by these models suffer from many problems such as responses not being contextualized and tend to generate generic responses that lack information content, damaging the user’s experience seriously. Therefore, many studies try introducing more information into the dialogue models to make the generated responses more vivid and informative. Unlike them, this paper improves the quality of generated responses by learning the implicit pattern information between contexts and responses in the training samples. In this paper, we first build an open-domain dialogue model based on the pre-trained language model (i.e., GPT-2). And then, an improved scheduled sampling method is proposed for pre-trained models, by which the responses can be used to guide the response generation in the training phase while avoiding the exposure bias problem. More importantly, we design a response-aware mechanism for mining the implicit pattern information between contexts and responses so that the generated replies are more diverse and approximate to human replies. Finally, we evaluate the proposed model (RAD) on the Persona-Chat and DailyDialog datasets;and the experimental results show that our model outperforms the baselines on most automatic and manual metrics. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-Label Text Classification for Judicial Texts via Dual Graph and Label Feature Fusion 10

Multi-Label Text Classification for Judicial Texts via Dual ...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Gu, Qiliang Lu, Qin Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Industrial Network and Information System Security Jinan China

ISBN: (纸本)9798331520861

The legal judgement prediction (LJP) of judicial texts represents a multi-label text classification (MLTC) problem, which in turn involves three distinct tasks: the prediction of charges, legal articles, and terms of penalty. Nevertheless, extant multi-label text classification models tend to eschew the consideration of multiple correlations and semantic information between labels when predicting judicial texts, which may result in the loss of pertinent information. Furthermore, these models do not take full advantage of the local and overall information of the labels in the process of selecting appropriate labels for the text using the multi-head attention mechanism. To address these issues, we propose a new model, BGFLFF, which explores label correlation and semantics among the three tasks by employing Graph Convolutional network (GCN) and multi-head attention mechanisms. In particular, we propose a Bi-Graph Fusion GCN (BGF-GCN), which fuses the co-occurrence matrix of labels with the cosine similarity matrix, thereby fully exploiting the multiple correlations between labels. Furthermore, prior to embedding the tags, the interpretations of the labels are obtained via Google in order to enhance the semantic information between the labels. To further reinforce the interconnections between labels and text and more effectively comprehend the interrelationships between the three tasks, we propose a Multi-Head Label Feature Fusion Attentional Mechanism (MH-LFFAtt), which assigns distinct weights to the pertinent label information in the text by fusing the local and overall features of the labels. The experimental results demonstrate that the F1 score exhibits an improvement of up to 2. 2 8 % and a minimum of 1. 2 9 % across the various tasks of the two datasets. This evidence substantiates the assertion that BGFLFF outperforms the existing baseline model. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Association Pattern-enhanced Molecular Representation Learning 39

Association Pattern-enhanced Molecular Representation Learni...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Jia, Lingxiang Ying, Yuchen Qiu, Tian Yao, Shaolun Xue, Liang Lei, Jie Song, Jie Song, Mingli Feng, Zunlei State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China Computing Science and Artificial Intelligence College Suzhou City University China College of Computer Science Zhejiang University of Technology China

ISBN: (纸本)157735897X

The applicability of drug molecules in various clinical scenarios is significantly influenced by a diverse range of molecular properties. By leveraging self-supervised conditions such as atom attributes and interatomic bonds, existing advanced molecular foundation models can generate expressive representations of these molecules. However, such models often overlook the fixed association patterns within molecules that influence physiological or chemical properties. In this paper, we introduce a novel association pattern-aware message passing method, which can serve as an effective yet general plug- and-play plugin, thereby enhancing the atom representations generated by molecular foundation models without requiring additional pretraining. Additionally, molecular property-specific pattern libraries are constructed to collect the generated interpretable common patterns that bind to these properties. Extensive experiments conducted on 11 benchmark molecular property prediction tasks across 8 advanced molecular foundation models demonstrate significant superiority of the proposed method, with performance improvements of up to approximately 20%. Furthermore, a property-specific pattern library is tailored for blood-brain barrier penetration, which has undergone corresponding mechanistic validation. Copyright © 2025, Association for the Advancement of Artificial Intelligence.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Learning for UAV Trajectory and Caching With Federated Cloud-Assisted Knowledge Distillation

引用

IEEE Transactions on network and Service Management 2025年第3期22卷 2516-2533页

作者： Tietaa Maale, Gerald Arden Elorm Kuadey, Noble Arafat, Yeasin Thomas, Kwantwi Sun, Guolin Liu, Guisong Research Institute of Intelligent Computing University of Electronic Science and Technology of China School of Computer Science and Engineering National Key Laboratory of Intelligent Collaborative Computing Chengdu611731 China McCoy University College of Education Department of Mathematics and ICT Nadowli Ghana Research Institute of Intelligent Computing at the University of Electronic Science and Technology of China School of Computer Science and Engineering National Key Laboratory of Intelligent Collaborative Computing Chengdu611731 China Ho Technical University Department of Computer Science Ho Ghana University of Mines and Technology Department of Computer Science and Engineering Tarkwa Ghana Southwestern University of Finance and Economics Complex Laboratory of New Finance and Economics School of Computing and Artificial Intelligence Chengdu610074 China Ministry of Education Engineering Research Center of Intelligent Finance Chengdu610030 China

The proliferation of Internet of Things (IoT) technologies and ubiquitous connectivity has led to uncrewed aerial vehicles (UAVs) playing key role as edge servers, revolutionizing the wireless communications landscape by facilitating computing and caching resources closer to ground users (GUs). This advancement significantly alleviates core network loads, reduces latency, and guarantees content availability even in congested or remote areas. However, jointly optimizing UAV caching strategies and trajectories gives rise to a multi-task optimization (MTO) problem. This paper introduces a novel multi-task geo-temporal caching (MT-GTC) framework that addresses the interplay between UAV caching mechanisms and trajectory optimization in a cohesive manner. Leveraging a proposed multi-task learning (MTL) model for joint optimization of UAV caching and trajectory design, we develop a federated learning cloud-assisted knowledge distillation (FL-CAKD) scheme to preserve data privacy and adapt to data heterogeneity. FL-CAKD transfers knowledge from a cloud model orchestrator (CMO), which houses a large and sophisticated teacher model, to a lightweight on-device MTL student models using soft target distributions instead of large model parameters, significantly reducing communication costs. MT-GTC optimizes caching and trajectories to maximize cache hits and minimize latency. Evaluations on real-world mobility datasets demonstrate up to 95% cache hit rates and 21% lower delays compared to baselines. © 2004-2012 IEEE.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Clustering Combination Method Using Intuitionistic Fuzzy Similarity in Software Module Clustering

Hierarchical Clustering Combination Method Using Intuitionis...

引用

2023 International Conference on networking and network Applications, NaNA 2023

作者： Xia, Hong Wang, Bo Zhang, Yongkang Chen, Yanping School of Computer Science and Technology Xi'an University of Posts and Telecommunications China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing China Xi 'An Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China

ISBN: (纸本)9798350327380

In order to solve the problem that the similarity method used in software module clustering can produce arbitrary decision, and the description matrix of dendrogram generated by base clustering in hierarchical clustering combination does not consider more characteristics of entities, a hierarchical clustering combination method based on intuitionistic fuzzy similarity (HCC-IFS) was proposed. In the process of entity similarity calculation, the intuitionistic fuzzy set theory and similarity calculation method are used to provide membership and non-membership attributes for each entity, so as to improve the merging efficiency and solve arbitrary decision problems. In the description matrix representation of base clustering, the absolute and relative features obtained from the dendrogram are used to construct the description matrix, and the generated description matrix is combined. Finally, the proposed algorithm is verified by experiments. Experimental results show that HCC-IFS can produce better clustering results and improve the recovery quality of software architecture. © 2023 IEEE.

关键词： Fuzzy set theory

来源：评论

学校读者我要写书评

暂无评论

Sensing–Communication–Computation Integration for Federated Edge Learning With Controllable Model Dropout

引用

IEEE Internet of Things Journal 2025年第12期12卷 19767-19781页

作者： Jiao, Xiang Zhu, Guangxu Jiang, Wei Chen, Li Luo, Wu Wen, Dingzhu Peking University State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Beijing100871 China Shenzhen Research Institute of Big Data Shenzhen International Center For Industrial and Applied Mathematics Shenzhen518172 China University of Science and Technology of China CAS Key Laboratory of Wireless Optical Communication Hefei230052 China ShanghaiTech University Network Intelligence Center School of Information Science and Technology Shanghai201210 China

Federated edge learning (FEEL) is an advanced paradigm in edge artificial intelligence, enabling privacy-preserving collaborative model training through periodic communication between edge devices and a central server. FEEL involves three key processes: 1) sensing;2) computation;and 3) communication for data acquisition, processing, and exchange, respectively. Due to limited system resources, optimizing each process individually may lead to suboptimal learning performance. This challenge has sparked research into integrated sensing-computation–communication (ISCC) design for enhanced FEEL. While previous work has optimized general learning parameters, such as batch size and computing frequency, there is a lack of customized designs considering the neural network architecture as an optimizable variable in ISCC for FEEL. To close this gap, we introduce a novel design where each device generates a submodel through controllable weight dropout, adding flexibility by directly manipulating the learning process and reducing computation and communication overhead. To guide ISCC resource allocation in this new setting, we present a comprehensive convergence analysis, revealing the tight coupling of sensing, computation, and communication across devices and their impact on FEEL convergence. Building on these theoretical insights, we formulate an ISCC problem aiming to maximize the FEEL convergence rate through joint optimization of variables, such as batch size, sensing power, dropout rate, and communication power. This nonconvex problem is decomposed into two subproblems via alternating optimization: one controls batch size using a sorting algorithm, while the other focuses on ISCC device parameters, transformable into a convex problem solved by successive convex approximation. Extensive experiments using human motion recognition datasets demonstrate the superiority of the proposed design over baseline schemes. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Task Separation and Knowledge Sharing for Class Incremental Learning 5

Task Separation and Knowledge Sharing for Class Incremental ...

引用

5th International Conference on Intelligent computing and Human-Computer Interaction, ICHCI 2024

作者： Zhang, Jiali Qiao, Xiaoyan School of Computer Science and Technology Shandong Technology and Business University Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion Technology and Evaluation Shandong Engineering Research Center Shandong Yantai China School of Mathematics and Information Science Shandong Technology and Business University Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion Technology and Evaluation Shandong Engineering Research Center Shandong Yantai China

ISBN: (纸本)9798350368284

Methods based on dynamically expanding architectures can effectively mitigate catastrophic forgetting in class incremental learning (CIL), but they often overlook information sharing and integration between subnetworks, leading to performance degradation and increased parameter count and memory consumption as the network expands. To address these complex issues, we introduce a new method called Task Separation and Knowledge Sharing (TSKS), which transfers knowledge at both the logical and feature levels through Hybrid Knowledge Distillation (HKD). In logical distillation, we combine Global Knowledge Distillation (GKD) and Task Knowledge Distillation (TKD) to establish connections between tasks. To prevent the model from favoring new classes, we design an Attention- Based Feature Fusion (ABFF) mechanism to capture important features. Additionally, we introduce a Soft-Margin Auxiliary Loss (SMAL) to help the model learn new concepts. Extensive experiments show that TSKS outperforms existing models on CIFAR100 and ImageNet100, regardless of whether memory samples are used. Notably, TSKS demonstrates superior performance in memory-free settings, indicating a reduced reliance on rehearsal memory. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Scale‐wise interaction fusion and knowledge distillation network for aerial scene recognition

引用

CAAI Transactions on Intelligence technology 2023年第4期8卷 1178-1190页

作者： Hailong Ning Tao Lei Mengyuan An Hao Sun Zhanxuan Hu Asoke K.Nandi School of Computer Science and Technology Xi'an University of Posts and TelecommunicationsShaanxi Key Laboratory of Network Data Analysis and Intelligent ProcessingXi'anChina Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'anChina School of Electronic Information and Artificial Intelligence Shaanxi University of Science and TechnologyXi'anChina School of Computer Central China Normal UniversityWuhanChina Department of Electronic and Electrical Engineering Brunel University LondonLondonUK Xi'an Jiaotong University Xi'anChina

Aerial scene recognition(ASR)has attracted great attention due to its increasingly essential *** of the ASR methods adopt the multi‐scale architecture because both global and local features play great roles in ***,the existing multi‐scale methods neglect the effective interactions among different scales and various spatial locations when fusing global and local features,leading to a limited ability to deal with challenges of large‐scale variation and complex background in aerial scene *** addition,existing methods may suffer from poor generalisations due to millions of to‐belearnt parameters and inconsistent predictions between global and local *** tackle these problems,this study proposes a scale‐wise interaction fusion and knowledge distillation(SIF‐KD)network for learning robust and discriminative features with scaleinvariance and background‐independent *** main highlights of this study include two *** the one hand,a global‐local features collaborative learning scheme is devised for extracting scale‐invariance features so as to tackle the large‐scale variation problem in aerial scene ***,a plug‐and‐play multi‐scale context attention fusion module is proposed for collaboratively fusing the context information between global and local *** the other hand,a scale‐wise knowledge distillation scheme is proposed to produce more consistent predictions by distilling the predictive distribution between different scales during *** experimental results show the proposed SIF‐KD network achieves the best overall accuracy with 99.68%,98.74%and 95.47%on the UCM,AID and NWPU‐RESISC45 datasets,respectively,compared with state of the arts.

关键词： deep learning image analysis image classification information fusion

来源：评论

学校读者我要写书评

暂无评论

RENN: A Rule Embedding Enhanced Neural network Framework for Temporal Knowledge Graph Completion 30

RENN: A Rule Embedding Enhanced Neural Network Framework for...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zong, Linlin Xie, Zhenrong Ma, Chi Liu, Xinyue Zhang, Xianchao Xu, Bo Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province School of Software Dalian University of Technology China School of Computer Science and Technology Dalian University of Technology China Key Laboratory of Social Computing and Cognitive Intelligence Dalian University of Technology Ministry of Education China

ISBN: (纸本)9782493814104

Existing approaches encompass deep neural network-based methods for temporal knowledge graph embedding and rule-based logical symbolic reasoning. However, the former may not adequately account for structural dependencies between ***, the latter methods relies heavily on strict logical rule reasoning and lacks robustness in the face of fuzzy or noisy data. In response to these challenges, we present RENN, a groundbreaking framework that enhances temporal knowledge graph completion through rule embedding. RENN employs a three-step approach. First, it utilizes temporary random walk to extract temporal logic rules. Then, it pre-trains by learning embeddings for each logical rule and its associated relations, thereby enhancing the likelihood of existing quadruples and logical rules. Finally, it incorporates the embeddings of logical rules into the deep neural network. Our methodology has been validated through experiments conducted on various temporal knowledge graph models and datasets, consistently demonstrating its effectiveness and potential in improving temporal knowledge graph completion. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo 39

DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Yuan, Zhenlong Luo, Jinguo Shen, Fei Li, Zhaoxin Liu, Cong Mao, Tianlu Wang, Zhaoqi Institute of Computing Technology Chinese Academy of Sciences China Harbin Institute of Technology Shenzhen China Nanjing University of Science and Technology Nanjing China Agricultural Information Institute Chinese Academy of Agricultural Sciences China Key Laboratory of Agricultural Big Data Ministry of Agriculture and Rural Affairs China

ISBN: (纸本)157735897X

Patch deformation-based methods have recently exhibited substantial effectiveness in multi-view stereo, due to the incorporation of deformable and expandable perception to reconstruct textureless areas. However, such approaches typically focus on exploring correlative reliable pixels to alleviate match ambiguity during patch deformation, but ignore the deformation instability caused by mistaken edge-skipping and visibility occlusion, leading to potential estimation deviation. To remedy the above issues, we propose DVP-MVS, which innovatively synergizes depth-edge aligned and cross-view prior for robust and visibility-aware patch deformation. Specifically, to avoid unexpected edge-skipping, we first utilize Depth Anything V2 followed by the Roberts operator to initialize coarse depth and edge maps respectively, both of which are further aligned through an erosion-dilation strategy to generate fine-grained homogeneous boundaries for guiding patch deformation. In addition, we reform view selection weights as visibility maps and restore visible areas by cross-view depth reprojection, then regard them as cross-view prior to facilitate visibility-aware patch deformation. Finally, we improve propagation and refinement with multi-view geometry consistency by introducing aggregated visible hemispherical normals based on view selection and local projection depth differences based on epipolar lines, respectively. Extensive evaluations on ETH3D and Tanks & Temples benchmarks demonstrate that our method can achieve state-of-the-art performance with excellent robustness and generalization. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

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

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

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：