检索结果-内蒙古大学图书馆

Faster Zero-shot Multi-modal Entity Linking via Visual-Linguistic Representation

Data Intelligence 2022年第3期4卷 493-508页

作者： Qiushuo Zheng Hao Wen Meng Wang Guilin Qi Chaoyu Bai School of Cyber Science and Engineering Southeast UniversityNanjing 211189China School of Computer Science and Engineering Southeast UniversityNanjing 211189China Key Laboratory of Computer Network and Information Integration(Southeast University) Ministry of EducationNanjing 211189China

Multi-modal entity linking plays a crucial role in a wide range of knowledge-based modal-fusion tasks, i.e., multi-modal retrieval and multi-modal event extraction. We introduce the new ZEro-shot Multi-modal Entity Linking(ZEMEL) task, the format is similar to multi-modal entity linking, but multi-modal mentions are linked to unseen entities in the knowledge graph, and the purpose of zero-shot setting is to realize robust linking in highly specialized domains. Simultaneously, the inference efficiency of existing models is low when there are many candidate entities. On this account, we propose a novel model that leverages visuallinguistic representation through the co-attentional mechanism to deal with the ZEMEL task, considering the trade-off between performance and efficiency of the model. We also build a dataset named ZEMELD for the new task, which contains multi-modal data resources collected from Wikipedia, and we annotate the entities as ground truth. Extensive experimental results on the dataset show that our proposed model is effective as it significantly improves the precision from 68.93% to 82.62% comparing with baselines in the ZEMEL task.

关键词： Knowledge Graph Multi-modal Learning Poly Encoders

来源：评论

学校读者我要写书评

暂无评论

A Constructive Method Based on Dynamic Solution Space for Travelling Salesman Problem 11

A Constructive Method Based on Dynamic Solution Space for Tr...

引用

11th International Conference on Advanced Cloud and Big Data, CBD 2023

作者： Bai, Xiaoxin Luli, Luli Wu, Hanqian Southeast University School of Computer Science and Engineering China Southeast University School of Cyber Science and Engineering China Suzhou Centennail College China Southeast University Key Laboratory of Computer Network and Information Integration of Ministry of Education China

ISBN: (纸本)9798350345346

Neural combinatorial optimization (NCO) has emerged as a promising field to solve the combinatorial optimization problem (COP) as automatically learning the solvers less relying on domain-specific expert knowledge. Constructive Method (ConsM) is the most widely used approach in NCO for solving various COPs and their variations. However, few literature elucidates the underlying principles of ConsM, hindering further optimization. In this paper, we analyze the efficiency principle of ConsM for COPs from the perspective of discrete solution space and summarize its design principles. These principles can serve as guidelines for designing novel constructive policy. Based on these principles, we reviewed the existing ConsM models and identified that the design of existing decoder introduced certain noises, which negatively impacted the policy performance. Therefore, we designed a novel decoder in line with the aforementioned principles. Notably, our method can be applied to all ConsM models and yielded significant improvements compared to the original. We evaluated our method on Traveling Salesman Problem(TSP) and the experimental results verified the effectiveness and efficiency of our method, supporting our analysis of ConsM. In particular, we reduced the average optimality gap from 1.16% to 0.62% for TSP100 compared to Sym-NCOs, keeping the hyperparameters constant. © 2023 IEEE.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

Generalization analysis for multi-label learning 24

Generalization analysis for multi-label learning

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Yi-Fan Zhang Min-Ling Zhang School of Cyber Science and Engineering Southeast University Nanjing China and Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education China Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education China and School of Computer Science and Engineering Southeast University Nanjing China

Despite great advances in algorithms for multilabel learning, research on the theoretical analysis of generalization is still in the early stage. Some recent theoretical results has investigated the generalization performance of multi-label learning under several evaluation metrics, however, how to reduce the dependency on the number of labels, explicitly introduce label correlations, and quantitatively analyze the impact of various inductive biases in the generalization analysis of multi-label learning is still a crucial and open problem. In an attempt to make up for the gap in the generalization theory of multi-label learning, we develop several novel vector-contraction inequalities, which exploit the Lipschitz continuity of loss functions, and derive generalization bounds with a weaker dependency on the number of labels than the state of the art in the case of decoupling the relationship among different components, which serves as theoretical guarantees for the generalization of multilabel learning. In addition, we derive the generalization bound for Macro-Averaged AUC and analyze its relationship with class-imbalance. The mild bounds without strong assumptions explain the good generalization ability of multi-label learning with first-order label correlations and high-order label correlations induced by norm regularizers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Complementary Classifier Induced Partial Label Learning

arXiv

引用

arXiv 2023年

作者： Jia, Yuheng Si, Chongjie Zhang, Min-Ling Key Laboratory of Computer Network and Information Integration School of Computer Science and Engineering Nanjing210096 China MoE Key Lab of Artificial Intelligence AI Institute Shanghai200240 China

In partial label learning (PLL), each training sample is associated with a set of candidate labels, among which only one is valid. The core of PLL is to disambiguate the candidate labels to get the ground-truth one. In disambiguation, the existing works usually do not fully investigate the effectiveness of the non-candidate label set (a.k.a. complementary labels), which accurately indicates a set of labels that do not belong to a sample. In this paper, we use the non-candidate labels to induce a complementary classifier, which naturally forms an adversarial relationship against the traditional PLL classifier, to eliminate the false-positive labels in the candidate label set. Besides, we assume the feature space and the label space share the same local topological structure captured by a dynamic graph, and use it to assist disambiguation. Extensive experimental results validate the superiority of the proposed approach against state-of-the-art PLL methods on 4 controlled UCI data sets and 6 real-world data sets, and reveal the usefulness of complementary learning in PLL. The code has been released in the link https://***/Chongjie-Si/PL-CL. Copyright © 2023, The Authors. All rights reserved.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Deep Spatial Spectral Convolutional Sparse Coding for Spectral CT Image Reconstruction

Deep Spatial Spectral Convolutional Sparse Coding for Spectr...

引用

International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)

作者： Jin Liu Jingjing Xie Kun Wang Jun Qiang College of Computer and Information Anhui Polytechnic University Wuhu China Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University Nanjing China

ISBN: (数字)9798331507398

ISBN: (纸本)9798331507404

Spectral computed tomography (CT) provides the potential to generate attenuation maps at varying spectral bins, which can subsequently be employed for the resolve of tissue materials. However, the majority of reconstruction algorithms employed for every projection energy bin typically exhibit a considerable degree of noise. Recently, a series of techniques have been designed in spectral CT reconstruction based on traditional iterative models or deep learning (DL) methods. However, these works are independent or simply coupled, often neglecting the dependency relationships of spatial and spectrum. Additionally, the interpretability and generalization capabilities remain as formidable challenges for current methods. To effectively address these challenges, we initially introduce a spatial-spectral convolutional sparse coding (SS-CSC) framework, which aims to jointly represent spatial and spectral features in a unified manner. Subsequently, we devise a novel deep unfolding network, inspired by SS-CSC, for spectral CT image representation. We refer to this component as the SS-CSC module. Furthermore, we expand the iterative reconstruction scheme for constructing an interpretable deep SS-CSC iterative reconstruction network (SS-CSC-Net) model for spectral CT imaging. The SS-CSC-Net is composed of several iteration blocks, with each block containing two modules: image reconstruction and SS-CSC modules. The spectral CT image is updated using a deep learning-based spatial-spectral prior constraint. Experimental results from both qualitative results and quantitative analyses indicate that the proposed SS-CSC-Net excels in noise reduction and in maintaining tissue edge integrity, delivering superior overall performance.

关键词： Convolutional codes Training Statistical analysis Computed tomography Noise reduction Training data Iterative methods Image reconstruction Unsupervised learning Testing

来源：评论

学校读者我要写书评

暂无评论

ACDNet: Attention-guided Collaborative Decision network for Effective Medication Recommendation

arXiv

引用

arXiv 2023年

作者： Mi, Jiacong Zu, Yi Wang, Zhuoyuan He, Jieyue School of Computer Science and Engineering Key Lab of Computer Network and Information Integration MOE Southeast University Jiangsu Nanjing210018 China

Medication recommendation using Electronic Health Records (EHR) is challenging due to complex medical data. Current approaches extract longitudinal information from patient EHR to personalize recommendations. However, existing models often lack sufficient patient representation and overlook the importance of considering the similarity between a patient’s medication records and specific medicines. Therefore, an Attention-guided Collaborative Decision network (ACDNet) for medication recommendation is proposed in this paper. Specifically, ACDNet utilizes attention mechanism and Transformer to effectively capture patient health conditions and medication records by modeling their historical visits at both global and local levels. ACDNet also employs a collaborative decision framework, utilizing the similarity between medication records and medicine representation to facilitate the recommendation process. The experimental results on two extensive medical datasets, MIMIC-III and MIMIC-IV, clearly demonstrate that ACDNet outperforms state-of-the-art models in terms of Jaccard, PR-AUC, and F1 score, reaffirming its superiority. Moreover, the ablation experiments provide solid evidence of the effectiveness of each module in ACDNet, validating their contribution to the overall performance. Furthermore, a detailed case study reinforces the effectiveness of ACDNet in medication recommendation based on EHR data, showcasing its practical value in real-world healthcare scenarios. © 2023, CC BY.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

A community detection model based on hierarchical graph clustering network with probability distribution

引用

Kongzhi yu Juece/Control and Decision 2025年第6期40卷 1969-1974页

作者： Xu, Sen Liu, Xuan-Qi Chen, Chao-Feng Guo, Nai-Xuan Bian, Xue-Sheng Ma, Fu-Rong Hua, Xiao-Peng Zhou, Tian School of Information Engineering Yancheng Institute of Technology Yancheng224051 China Key Laboratory of Computer Network and Information Integration Southeast University Nanjing210000 China School of Underwater Sound Engineering Harbin Engineering University Harbin150001 China

In order to capture the hidden structure of networks and reduce the dependence of community detection models on the choice of initial parameters, this paper proposes a community detection model based on hierarchical graph clustering networks with probability distribution (HGCPD). Firstly, graph convolutional networks are utilized to learn and cache feature representations of nodes in the graph. Then, a hierarchical clustering method based on node pair similarity probability is introduced to recursively construct community structures at different levels. Finally, the problem of model hyperparameter optimization is explored, and the Bayesian optimization methods are designed to automatically adjust parameters, thereby improving the efficiency of the model. Experiments on multiple network datasets of different scales show that the HGCPD model is superior to mainstream methods in terms of the accuracy and effectiveness of community detection, and the model's interpretability is verified through visualization. © 2025 Northeast University. All rights reserved.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

YOLOv8-GR: Gesture Recognition by Improving of YOLOv8 Algorithm

YOLOv8-GR: Gesture Recognition by Improving of YOLOv8 Algori...

引用

International Conference on Advanced Cloud and Big Data (CBD)

作者： Yi Ding Naixuan Guo Haitao Meng School of Information Engineering Yancheng Institute of Technology Yancheng China Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education

ISBN: (数字)9798331511074

ISBN: (纸本)9798331511081

Gesture recognition has been widely used in many situations, such as human-computer interaction, virtual reality and smart home. To meet the current demands for accuracy and speed in gesture recognition, this paper proposes an improved algorithm based on YOLOv8, referred to as YOLOv8-GR. By replacing the original YOLOv8 detection head with a Dynamic Head, we integrate scale-aware, spatial-aware, and task-aware attention mechanisms within a unified framework. To enhance context information capture, the SPPF (Spatial Pyramid Pooling - Fast) module is optimized to a modified SPPF-LSKA (Large Separable Kernel Attention) module. In addition, we employ the EIoU loss function for more accurate evaluation of object detection results. To evaluate our algorithm, we integrate a gesture dataset in complex and diverse scenarios through network and field shooting annotations. Compared to the original YOLOv8, the proposed YOLOv8-GR achieves a 22.5% improvement in mAP50 and a 10.0% improvement in mAP50-95 on our dataset. We also compare YOLOv8-GR with the MobileNetv2-based SSD, which is a kind of one-stage object detection algorithm. While maintaining similar recognition accuracy, the computational cost of YOLOv8-GR is 9.9 GFLOPs, which is 15.8% of SSD, and our algorithm can be deployed on Raspberry Pi 4B.

关键词： Human computer interaction Solid modeling Accuracy Convolution Heuristic algorithms Gesture recognition Object detection Virtual reality Smart homes Kernel

来源：评论

学校读者我要写书评

暂无评论

Early Prediction of Heart Disease via LSTM-XGBoost 23

Early Prediction of Heart Disease via LSTM-XGBoost

引用

9th International Conference on Computing and Artificial Intelligence, ICCAI 2023

作者： Zang, Xiaodong Du, Jin Song, Yuansheng School of Cyber Science and Engineering Qufu Normal University Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University Nanjing211189 China School of Cyber Science and Engineering Qufu Normal University China

ISBN: (纸本)9781450399029

With the development of information and technology, especially with the boom in big data, healthcare support systems are becoming much better. However, an early diagnosis is not an easy task because it is hard to find out the hidden patterns in the disease. The symptoms of heart failure are usually non-specific. Therefore, this study aims to devise an early prediction model for incident heart disease based on machine learning algorithms. In this study, we compared several powerful models, including support vector machines (SVM), k-nearest neighbor (KNN), decision tree, extreme gradient boosting (XGBoost), random forest, gradient boosting decision tree (GBDT), categorical boosting (CatBoost), light gradient boosting machine (LightGBM), and choose two best models, namely, XGBoost and LSTM as our prediction model. The XGBoost algorithm was used to extract a subset from the data of patients, which will be fed into the LSTM-XGBoost model for training. An experiment comparison is conducted based on the data from Kaggle. Experimental results demonstrate that the LSTM-XGBoost model can operate effectively with a prediction accuracy achieving 0.9896 and a loss rate achieving 0.0105, which is much better than XGBoost or LSTM, respectively. © 2023 Copyright held by the owner/author(s).

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Deep Iterative Reconstruction network Based on Residual Constraint for Low-Dose CT Imaging 8

Deep Iterative Reconstruction Network Based on Residual Cons...

引用

8th International Conference on Systems and Informatics, ICSAI 2022

作者： Liu, Jin Kang, Yanqin Liu, Tao Zhang, TingYu Zhang, Yikun Anhui Polytechnic University School of Computer and Information Wuhu China Southeast University Ministry of Education Key Laboratory of Computer Network and Information Integration Nanjing China Southeast University School of Computer Science and Engineering Nanjing China

ISBN: (纸本)9781665474481

clinical low X-ray dose computed tomography (LDCT) scanner often induce high intensity strip artifact and spot nosie, compromising diagnoses and intervention plans. Recently, sparsely constrained and network learning-based frameworks have been shown to be efficient in mitigating such issue. In this work, we propose a deep iterative reconstruction network (DIRNet) model with a residual constraint to synergize the advantages of feature learning and image reconstruction to address the LDCT imaging problem. DIR-Net compose by few iteration units, and all iteration units include three different network modules: projection restoration, residual constraint and image update block. DIR-Net is a promising approach for building an end-to-reconstruction mapping strategy and directly obtaining high-quality CT images. Furthermore, LISTA is used to conFigure the network, and the whole network architecture yields improved interpretability. Qualitative and quantitative analysis in test data shown the promising imaging effects of DIR-Net in quantum noise reduction, block artifact removal and tissue detail texture mantian. © 2022 IEEE.

关键词： Image reconstruction

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：