检索结果-内蒙古大学图书馆

14th International Conference on Measuring technology and Mechatronics Automation, ICMTMA 2022

作者： Qiang, Chengyu Li, Xiaogo Ma, Xianyan Han, Wei Yao, Yi School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Xi'an71012 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi'an710121 China Xi 'an Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China

ISBN: (纸本)9781665499781

Entity disambiguation based on entity-link is a technique which constructs the mappings between entity reference items appearing in the short text and target entity in knowledge base respectively. In this paper we propose an entity disambiguation method based on Graph Attention networks for semi-structured knowledge base data. First, a global Knowledge Graph is constructed from the semi-structured knowledge base, and the entity reference items are embedded by Bert pre-trained model meanwhile. Next, Graph Attention networks which leverages masked self-attention layers is applyed on candidate entity nodes of global Knowledge Graph to fetch a vector of node level. Furtherly, we compute similarity scores rank between the entity reference items and the candidate entity to complete the task of entity disambiguation. The experimental results on CCKS2019 dataset achieve state-of-the-art. © 2022 IEEE

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Dts-Adapstnet: An Adaptive Spatiotemporal Neural networks for Traffic Prediction with Mulit-Graph Fusion

SSRN

引用

SSRN 2024年

作者： Zhang, Jing Shi, Wenlong Zhong, Xiangxuan Chen, Xiaoping Ye, Xiucai School of Computer Science and Mathematics Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China Department of Computer Science University of Tsukuba Tsukuba Japan

Traffic prediction is of vital importance in intelligent transportation systems. It enables efficient route planning, congestion avoidance, and reduction of travel time, etc. However, accurate road traffic prediction is challenging due to the complex spatio-temporal dependencies within the traffic network. Establishing and learning spatial dependencies are pivotal for accurate traffic prediction. Unfortunately, many existing methods for capturing spatial dependencies only consider single relationships, disregarding potential temporal and spatial correlations within the traffic network. Moreover, the end-to-end training methods often lack control over the training direction during graph learning. Additionally, existing traffic forecasting methods often fail to integrate multiple traffic data sources effectively, which affects prediction accuracy adversely. In order to capture the spatiotemporal dependencies of the traffic network accurately, a novel traffic prediction framework, Adaptive Spatio-Temporal Graph Neural Network based on Multi-graph Fusion (DTS-adapSTNet), is proposed. Firstly, in order to better extract the hidden spatial dependencies, a method of fusing multiple factors is designed, which includes the distance relationship, transfer relationship and same-road segment relationship of traffic data. Secondly, an adaptive learning method is proposed, which can control the learning direction of parameters better by the adaptive matrix generation module and traffic prediction module. Thirdly, an improved loss function is designed for training processes and a multi-matrix fusion module is designed to perform weighted fusion of the learned matrices, updating the spatial adjacency matrix continuously, which fuses as much traffic information as possible for more accurate traffic prediction. Finally, experimental results using two large real-world datasets demonstrate that the DTS-adapSTNet model outperforms other baseline models in terms of MAE, RMSE, and MAPE wh

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

VERO: Verification and Zero-Shot Feedback Acquisition for Few-Shot Multimodal Aspect-Level Sentiment Classification 39

VERO: Verification and Zero-Shot Feedback Acquisition for Fe...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Sun, Kai Wu, Hao Shi, Bin Mensah, Samuel Liu, Peng Dong, Bo Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University China School of Computer Science and Technology Xi’an Jiaotong University China School of computer science and engineering Guangxi Normal University Guilin China Department of Computer Science University of Sheffield Sheffield United Kingdom School of Continuing Education Xi’an Jiaotong University China

ISBN: (纸本)157735897X

Deep learning approaches for multimodal aspect-level sentiment classification (MALSC) often require extensive data, which is costly and time-consuming to obtain. To mitigate this, current methods typically fine-tune small-scale pretrained models like BERT and BART with few-shot examples. While these models have shown success, Large Vision-Language Models (LVLMs) offer significant advantages due to their greater capacity and ability to understand nuanced language in both zero-shot and few-shot settings. However, there is limited work on fine-tuning LVLMs for MALSC. A major challenge lies in selecting few-shot examples that effectively capture the underlying patterns in data for these LVLMs. To bridge this research gap, we propose an acquisition function designed to select challenging samples for the few-shot learning of LVLMs for MALSC. We compare our approach, Verification and ZERO-shot feedback acquisition (VERO), with diverse acquisition functions for few-shot learning in MALSC. Our experiments show that VERO outperforms prior methods, achieving an F1 score improvement of up to 6.07% on MALSC benchmark datasets. © 2025, Association for the Advancement of Artificial.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

A Multi-objective Perspective Towards Improving Meta-Generalization

A Multi-objective Perspective Towards Improving Meta-General...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Weiduo Liao Ying Wei Qirui Sun Qingfu Zhang Hisao Ishibuchi Department of Computer Science City University of Hong Kong Department of Computer Science and Engineering Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Southern University of Science and Technology School of Computer Science and Engineering Nanyang Technological University

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

To improve meta-generalization, i.e., accommodating out-of-domain meta-testing tasks beyond meta-training ones, is of significance to extending the success of meta-learning beyond standard benchmarks. Previous heterogeneous meta-learning algorithms have shown that tailoring the global meta-knowledge by the learned clusters during meta-training promotes better meta-generalization to novel meta-testing tasks. Inspired by this, we propose a novel multi-objective perspective to sharpen the compositionality of the meta-trained clusters, through which we have empirically validated that the meta-generalization further improves. Grounded on the hierarchically structured meta-learning framework, we formulate a hypervolume loss to evaluate the degree of conflict between multiple cluster-conditioned parameters in the two-dimensional loss space over two randomly chosen tasks belonging to two clusters and two mixed tasks imitating out-of-domain tasks. Experimental results on more than 16 few-shot image classification datasets show not only improved performance on out-of-domain meta-testing datasets but also better clusters in visualization.

关键词： Metalearning Visualization Neural networks Clustering algorithms Benchmark testing Standards Image classification

来源：评论

学校读者我要写书评

暂无评论

User Information Enhanced Knowledge Graph Convolutional networks for Recommender Systems 14

User Information Enhanced Knowledge Graph Convolutional Netw...

引用

14th International Conference on Measuring technology and Mechatronics Automation, ICMTMA 2022

作者： Hao, Junyu Li, Xiaoge School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Xi'an71012 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi'an710121 China Xi'an Key laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China

ISBN: (纸本)9781665499781

To deeply excavate the information contained in user data and better alleviate cold start problem, we propose KGCN++, a user information enhanced knowledge graph convolutional networks model for recommender system, which simulates nerves' influence diffusion of information of user and items in a unified framework. The model combines user information and user-item interaction information into a user knowledge graph, which advances KGCN by injecting high-order user potential information reflected in user graph and high-order influence of items reflected in item knowledge graph. In addition, we have designed the influence factors of different items on users, which are used to characterize the weight of items on the user's information dissemination, so as to distinguish users with different information. Through extensive experiments on real-world datasets, we demonstrate that KGCN++ achieves substantial gains in a variety of ecenarios, including movie and book recommendation, better performance compared to the other methods. © 2022 IEEE

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Feature Selection based on Mutual Information

Privacy-Preserving Feature Selection based on Mutual Informa...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Ningning Wu Hongwei Li Hanxiao Chen Xilin Zhang Yingzhe Wang School of Computer Science and Engineering University of Electronic Science and Technology of China Sichuan China State Key Laboratory of Integrated Services Networks Xidian University Shaanxi China

In the context of collaborative data analysis or machine learning tasks (such as biomedical image segmentation for tumor region definition) involving multiple parties, secure feature selection protocols enable the parties to jointly select the most informative features while preserving their privacy from being exposed to others. However, current secure feature selection methods have several limitations: (1) they leak intermediate results during feature selection raises serious privacy concerns; (2)they cannot cover various scenarios comprehensively. To this end, we present a secure feature selection framework based on mutual information, which improves the privacy-preserving data preprocessing work. Specifically, the division protocol performs low-complexity interactive computations, reducing the time cost to $578^{th}$ of the original; besides, our logarithm protocol converts shared values through Beaver's triple, and increases the efficiency by up to 118 times. We conduct extensive experimental evaluations on diverse real-world datasets, and the results demonstrate that our framework achieves up to 28.5% accuracy improve-ment, thus effectively enhancing the privacy protection work of machine learning data preprocessing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data Leakage Attack via Backdoor Misclassification Triggers of Deep Learning Models 4

Data Leakage Attack via Backdoor Misclassification Triggers ...

引用

4th International Conference on Data Intelligence and Security, ICDIS 2022

作者： Yang, Xiangkai Luo, Wenjian Zhang, Licai Chen, Zhijian Wang, Jiahai School of Computer Science and Technology Harbin Institute of Technology Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Guangdong Shenzhen518055 China Peng Cheng Laboratory Guangdong Shenzhen518055 China Sun Yat-sen University School of Computer Science and Engineering Guangdong Guangzhou510275 China

ISBN: (数字)9781665459686

ISBN: (纸本)9781665459686

In recent years, deep neural networks (DNNs) have been successfully applied in various tasks, and various third-party models are available to data holders. However, data holders who blindly use third-party models to train on their data may lead to data leakage, resulting in serious data privacy problems. The Capacity Abuse Attack (CAA) is the state-of-the-art black-box attack method which uses the labels of the augmented malicious dataset to encode the information of the training data. However, the expanded malicious dataset in CAA are artificially synthesized, not natural images, and significantly different from the original training data. Thus these malicious images are easy to be detected. In our attack, we use a technique similar to generating poisoned datasets in backdoor attacks, make malicious data generated similar to real and natural images, and make our attack more concealed. Extensive experiments are conducted, and the results demonstrate that our attack can effectively obtain the private training data of data holders without significantly impacting the model's original task. © 2022 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Uplink Control Information Based Clustered Access and Discontinuous Reception Management for mMTC

引用

IEEE Communications Letters 2025年第6期29卷 1380-1384页

作者： Wang, Shao-Di Wang, Chang-Long Wang, Hui-Ming Zhou, Feng Leung, Victor C. M. Xidian University Key Laboratory of Electronic Information Countermeasure and Simulation Technology of Ministry of Education Xi’an710071 China Xi’an Jiaotong University School of Information and Communication Engineering Ministry of Education Key Lab for Intelligent Networks and Network Security Xi’an710049 China Shenzhen MSU BIT University Artificial Intelligence Research Institute Shenzhen518172 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China The University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T 1Z4 Canada

Uplink control information (UCI) and discontinuous reception (DRX) play important roles for massive machine type communication (mMTC). Despite their standalone significance, a conspicuous gap exists in comprehensively exploring the synergy between UCI and DRX concerning both energy conservation and latency reduction for mMTC. In this letter, we propose a UCI-based clustered access and DRX management (UCADM) scheme that strikes a balance between these two critical performance metrics, reducing energy usage while preserving low latency in uplink-downlink interaction for mMTC. Specifically, we present a strictly feasible solution for the proposed UCADM scheme by using the spectral radius and the constraint projection, which can effectively solve DRX switching operations as indicated by scheduling information from UCI. Simulation results confirm the effectiveness of our scheme. © 1997-2012 IEEE.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

A Perturbation-Based Policy Distillation Framework with Generative Adversarial Nets

A Perturbation-Based Policy Distillation Framework with Gene...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Lihua Zhang Quan Liu Xiongzhen Zhang Yapeng Xu School of Computer Science and Technology Soochow University Suzhou China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou China

We study the problem of imitation learning in automated decision systems, in which a learner is trained to imitate an expert demonstrator. A widely used method is adversarial imitation learning that alternately optimizes a generator (learner) and a discriminator (reward function). However, the discriminator is biased during the initial and intermediate training stages. Consequently, the gradient descent direction of the learner is misguided, which leads to unstable training and sample complexity. In this paper, we propose deep imitation learning through a guidance-based policy distillation (GIL) algorithm. First, GIL proposes a teacher model, the guidance-based variational autoencoder, which is pre-trained with expert demonstrations. Then, GIL proposes a perturbation-based policy distillation method that uses the teacher model to guide the learner in the correct optimization direction, enabling the learner to imitate the expert policy with fewer detours. The experimental results show that our approach achieve higher sample efficiency compared with multiple baselines.

关键词： Training Legged locomotion Signal processing algorithms Grasping Signal processing Generators Task analysis

来源：评论

学校读者我要写书评

暂无评论

KAC-Unet: A Medical Image Segmentation With the Adaptive Group Strategy and Kolmogorov-Arnold Network

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Lin, Shiying Hu, Rong Li, Zuoyong Lin, Qinghua Zeng, Kun Wu, Xiang Fujian University of Technology Fujian Provincial Key Laboratory of Big Data Mining and Applications School of Computer Science and Mathematics Fuzhou350118 China Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control School of Computer and Big Data Fuzhou350121 China Fuzhou University Affiliated Provincial Hospital Provincial Clinical Medical College Fujian Medical University Department of Urology Fuzhou350001 China

In the field of deep learning-based medical image segmentation, convolutional neural networks (CNNs) extract image features by combining linear convolutional layers with nonlinear activation functions. However, excessive stacking of linear layers in the network limits the model’s ability to capture fine-grained details. In addition, the feature distribution imbalance caused by the traditional fixed grouping strategy (FGS) can affect the deep model’s capacity to perceive the overall structure of the image. To address these challenges, we propose a medical image segmentation framework, called Kolmogorov-Arnold Network with the adaptive group strategy and contextual Transformer based on Unet (KAC-Unet). First, we propose the adaptive group strategy (AGS) to balance the grouping of different input channels, alleviating the performance degradation caused by differences in group information. Then, we propose the Shift Tokenized Kolmogorov-Arnold Network (KAN) Block to capture complex features in medical images through flexible nonlinear transformations and shift operations. Extensive experiments are conducted on three medical image segmentation datasets. The results demonstrate the effectiveness and superiority of our proposed method compared with state-of-the-art algorithms. © 1963-2012 IEEE.

关键词： Convolutional neural networks

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：