检索结果-内蒙古大学图书馆

CSBNC-PAL: Consistency Semi-supervised Brain Network Classification Framework with Prototypical-Adversarial Learning

引用

IEEE Journal of Biomedical and Health Informatics 2025年 PP卷 PP页

作者： Ji, Junzhong Liu, Gan Wang, Xingyu Beijing University of Technology Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology College of Computer Science Beijing Artificial Intelligence Institute Beijing100124 China

In recent years, semi-supervised learning (SSL) for functional brain network (FBN) classification has gained considerable attention due to its potential to leverage large amounts of unlabeled data from multisite. However, existing SSL methods often struggle to address the distributional differences across different sites, which limits their ability to extract discriminative features from the unlabeled data, thus hindering classification performance. To overcome this challenge, we propose a novel consistency semi-supervised FBN classification framework with prototypical-adversarial learning, termed CSBNC-PAL. Specifically, we first design a contrastive consistency module (CCM) that utilizes contrastive learning to more effectively exploit unlabeled data and learn preliminary feature representations. Then, we introduce a prototype alignment module (PAM) that computes site-aware prototypes through weighted feature clustering to guide inter-site feature alignment, and achieve inter-site equilibrium feature representations. Finally, we develop an adversarial alignment module (AAM) that employs site-discriminative adversarial training based on a gradient reversal layer to guide intra-site feature alignment, and learn site-invariant features. The three modules above are optimized collectively in an end-to-end manner, ensuring effective learning from both labeled and unlabeled data while alleviating the distribution differences of multisite data. Experiments on the ABIDE I, ABIDE II, and ADHD-200 datasets demonstrate that the CSBNC-PAL outperforms many state-of-the-art SSL methods in FBN classification. © 2013 IEEE.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

MCVIE: An Effective Batch-Mode Active Learning for Multi-label Text Classification 12th

MCVIE: An Effective Batch-Mode Active Learning for Multi-lab...

引用

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

作者： Cheng, Xuan Zhou, Feng Wang, Qing Wang, Yitong Wang, Yiting Key Laboratory of Intelligent Telecommunications Software and Multimedia Beijing China School of Computer Science Beijing University of Posts and Telecommunications Beijing China JiuTian Team China Mobile Research Institute Beijing China

ISBN: (纸本)9783031446924

Data labeling for multi-label text is a challenging task in natural language processing, and active learning has emerged as a promising approach to reduce annotation effort while improving model performance. The primary challenge in multi-label active learning is to develop query strategies that can effectively select the most valuable unlabeled instances for annotation. Batch-mode active learning approaches, which select a batch of informative and diverse instances in each iteration, have been considered useful for improving annotation efficiency. However, challenges such as incomplete information ranking and high computational costs still hinder the progress of batch-mode methods. In this paper, we propose MCVIE, a novel batch-mode active learning method for multi-label text. MCVIE employs a two-stage active learning query strategy. Firstly, we combine two measures of prediction uncertainty and category vector inconsistency to calculate the basic information score for each example-label pair. Then, we use the Euclidean distance of text feature vectors to iteratively select diverse and informative example-label pairs for annotation. Experimental results on three benchmark datasets demonstrate that MCVIE outperforms other competitive methods. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Research and Implementation of Host Behavior Anomaly Detection technology Based on Deep Learning 25

Research and Implementation of Host Behavior Anomaly Detecti...

引用

25th IEEE International Conference on computer Supported Cooperative Work in Design, CSCWD 2022

作者： Zhang, Hang Gu, Yonghao Chai, Xiaolin Qi, Peng Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia Beijing University of Posts and Telecommunications Beijing100876 China Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia School of Computer Science Beijing University of Posts and Telecommunications Guangdong Provincial Key Laboratory of Information Security Technology Sun Yat-Sen University Beijing100876 China

ISBN: (纸本)9781665405270

In recent years, with the growth of network hosts and applications, Abnormal host behavior brings great challenges to the protection of user information privacy. Effective detection of abnormal host behavior is of great significance. Host anomaly detection technology can identify abnormal behaviors of the host by establishing the normal behavior benchmark, which is universal and capable of detecting new network attack behavior. However, the existing host behavior anomaly detection technology confronts with three problems(i.e., a large amount of data, difficulty in labeling, and strong manual dependence). To solve these problems, this paper proposes an unsupervised learning model based on BiGAN(Bidirectional Generative Adversarial Network) to detect abnormal host behavior. Our model introduces several loss functions and modifies them to apply to BiGAN. At the same time, we discuss which loss function is more suitable for host behavior anomaly detection. Experimental results show that the BiGAN model using the Hinge loss function is the most stable and has excellent anomaly detection performance. © 2022 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

RMGCN: Masked Graph Convolutional Networks for Relation-Aware Entity Alignment with Dangling Cases 12th

RMGCN: Masked Graph Convolutional Networks for Relation-Awa...

引用

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

作者： Liu, Xinyu Zhou, Feng Li, X.Y. Key Laboratory of Intelligent Telecommunications Software and Multimedia Beijing China School of Computer Science Beijing University of Posts and Telecommunications Beijing China School of Cyberspace Security Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9783031446924

Entity alignment (EA) is to match entities referring to identical real-world facts among different knowledge graphs (KGs). For simplicity, most previous work ignores the existence of dangling entities in the source KG. However, entity alignment task with dangling entities has emerged as a novel demand in real scenarios. Some work explores new dangling-aware loss functions and transfers existing methods on dangling settings, whose performance is still not satisfactory. Thus, in this work, we propose Relation-aware Masked Graph Convolutional Networks (RMGCN). In the learning stage, it can not only take advantage of the masking mechanism to alleviate the negative impact from nearby dangling neighbors, but also take both graph structure and relations of KGs into consideration. In the inference stage, it performs a two-step alignment which firstly filters out dangling entities, and then align the remaining entities. We adopt a novel distribution-based dangling entity detection method in first step to decrease the error propagation from dangling detection to the following EA task. The experimental results show that our model outperforms all state-of-the-art models with at least 7.5% on F1 score. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Tackling Real-world Complexity: Hierarchical Modeling and Dynamic Prompting for Multimodal Long Document Classification

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第6期35卷 5776-5790页

作者： Liu, Tengfei Hu, Yongli Li, Mingjie Yi, Junfei Chang, Xiaojun Gao, Junbin Yin, Baocai Beijing University of Technology Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing Institute of Artificial Intelligence School of Information Science and Technology Beijing100124 China Stanford University Department of Radiation Oncology StanfordCA94305 United States Hunan University National Engineering Laboratory of Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan Changsha410082 China University of Technology Sydney ReLER Laboratory Australian Artificial Intelligence Institute Faculty of Engineering and Information Technology UltimoNSW2007 Australia The University of Sydney Business School The University of Sydney Discipline of Business Analytics CamperdownNSW2006 Australia

With the rapid growth of internet content, multimodal long document data has become increasingly prominent, drawing significant attention from researchers. However, most existing methods primarily focus on scenarios where all modalities are present, often overlooking more challenging and realistic cases involving missing image modality. To address this limitation, we propose a robust multimodal long document classification (MLDC) framework that integrates hierarchical modeling and dynamic prompting to handle complex multimodal long document data. Our approach begins by leveraging hierarchical modeling combined with an Adaptive Correlation Multimodal Transformer (ACMT) to effectively capture relationships between text and images at both section and sentence levels. We also introduce a Dynamic Prompt Generation (DPG) module at both levels to enhance the model's robustness in handling missing image data. By evaluating sample uncertainty, the DPG module dynamically adjusts both the number of prompts and the prompts themselves, allowing the model to better adapt to the varying needs of different samples. Finally, a Hierarchical Heterogeneous Graph (HHG) is introduced to enhance feature interactions across levels, further improving the coherence and accuracy of the model. Extensive experiments on four multi-modal long document datasets demonstrate that our model shows superior performance compared to existing state-of-the-art MLDC classification methods in various conditions. © 1991-2012 IEEE.

关键词： Adaptation models Transformers Data models Correlation Circuits and systems Electronic mail Robustness Uncertainty Training Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Region feature smoothness assumption for weakly semi-supervised crowd counting

Region feature smoothness assumption for weakly semi-supervi...

引用

作者： Miao, Zhuangzhuang Zhang, Yong Piao, Xinglin Chu, Yi Yin, Baocai Beijing Key Laboratory of Multimedia and Intelligent Software Technology Faculty of Information Technology Beijing Institute of Artificial Intelligence Beijing University of Technology Beijing China China Electronics Technology Group Taiji Co. Ltd. Beijing China

Crowd counting is a hot issue in visual data processing. It also plays an important role in the field of video surveillance, social security, and traffic control. However, most of the existing crowd counting methods always adopt a mount of training data or point-level annotation to learn the mapping relationships between images and density maps, which would cost much human labor. In this paper, we propose a new weakly semi-supervised crowd counting method which uses less count-level data for data training. In particular, we extend the classical smoothness assumption and design a many-to-many Region Feature Smoothness Assumption to deal with the uneven density distribution problem within crowd region. Further, we adopt hypergraph representation to explore the complex high-order relationship for different crowd regions. Besides, we design a multi-scale dynamic hypergraph convolutional module and hyperedge contrastive loss. Extensive experiments have been conducted on five public datasets. The experimental results show that the proposed method outperforms the state-of-the-art ones. © 2023 John Wiley & Sons Ltd.

关键词： Traffic control

来源：评论

学校读者我要写书评

暂无评论

Scientific Paper Classification Based on Graph Neural Network with Hypergraph Self-attention Mechanism 8

Scientific Paper Classification Based on Graph Neural Networ...

引用

8th IEEE International Conference on Cloud Computing and Intelligence Systems, CCIS 2022

作者： Liu, Jiashun Xue, Zhe Li, Ang Beijing University of Posts and Telecommunications School of Computer Science Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia Beijing100876 China

ISBN: (纸本)9781665477352

The number of scientific papers has increased rapidly in recent years. How to make good use of scientific papers for research is very important. Through the high-quality classification of scientific papers, researchers can quickly find the resource content they need from the massive scientific resources. The classification of scientific papers will effectively help researchers filter redundant information, obtain search results quickly and accurately, and improve the search quality, which is necessary for scientific resource management. This paper proposed a science-technique paper classification method based on hypergraph neural network(SPHNN). In the heterogeneous information network of scientific papers, the repeated high-order subgraphs are modeled as hyperedges composed of multiple related nodes. Then the whole heterogeneous information network is transformed into a hypergraph composed of different hyperedges. The graph convolution operation is carried out on the hypergraph structure, and the hyperedges self-attention mechanism is introduced to aggregate different types of nodes in the hypergraph, so that the final node representation can effectively maintain high-order nearest neighbor relationships and complex semantic information. Finally, by comparing with other methods, we proved that the model proposed in this paper has improved its performance. © 2022 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Scientific and Technological News Recommendation Based on Knowledge Graph with User Perception 8

Scientific and Technological News Recommendation Based on Kn...

引用

8th IEEE International Conference on Cloud Computing and Intelligence Systems, CCIS 2022

作者： Zeng, Yuyao Du, Junping Xue, Zhe Li, Ang Beijing University of Posts and Telecommunications School of Computer Science Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia Beijing100876 China

ISBN: (纸本)9781665477352

Existing research usually utilizes side information such as social network or item attributes to improve the performance of collaborative filtering-based recommender systems. In this paper, the knowledge graph with user perception is used to acquire the source of side information. We proposed KGUPN to address the limitations of existing embedding-based and path-based knowledge graph-aware recommendation methods, an end-to-end framework that integrates knowledge graph and user awareness into scientific and technological news recommendation systems. KGUPN contains three main layers, which are the propagation representation layer, the contextual information layer and collaborative relation layer. The propagation representation layer improves the representation of an entity by recursively propagating embeddings from its neighbors (which can be users, news, or relationships) in the knowledge graph. The contextual information layer improves the representation of entities by encoding the behavioral information of entities appearing in the news. The collaborative relation layer complements the relationship between entities in the news knowledge graph. Experimental results on real-world datasets show that KGUPN significantly outperforms state-of-the-art baselines in scientific and technological news recommendation. © 2022 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Fast Text Classification by Leveraging Class Feature Words

Fast Text Classification by Leveraging Class Feature Words

引用

Chinese intelligent Automation Conference, CIAC 2021

作者： Yu, Bowen Du, Junping Shao, Yingxia Li, Ang Xu, Xin Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia School of Computer Science Beijing University of Posts and Telecommunications Beijing100876 China

ISBN: (纸本)9789811663710

Text classification is an important task in the NLP field, which aims to map documents into a set of predefined classes. Supervised machine learning or deep learning models have achieved great success in this field. However, these methods require a large number of high-quality labeled data and high performance machines for adequate training. In many cases, we cannot meet these conditions. In this paper, we propose a text classification algorithm leveraging class feature words. This method simulates the human’s intuition of document classification. First, we establish the feature word list of each class, then calculate the similarity between the document and feature word lists of classes and classify the document. The innovation of our method is that it doesn’t need external knowledge or a huge pre-trained language model. By establishing a class feature vocabulary and similarity analysis, we achieve the classification of words and documents. In order to verify its generality and robustness, we conduct experiments on 4 mainstream datasets and compare with the supervised text classification algorithms. The experiments show that our algorithm has extremely speed advantage, comparable to the performance of the supervised classification algorithm, and good interpretability. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

SIPR: Side-Information Pointwise Ranking Model for Scientific Research Project Query

SIPR: Side-Information Pointwise Ranking Model for Scientifi...

引用

Chinese intelligent Automation Conference, CIAC 2021

作者： Wang, Benzhi Kou, Feifei Du, Juping Xu, Mingying Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia School of Computer Science Beijing University of Posts and Telecommunications Beijing100876 China

ISBN: (纸本)9789811663710

Learning to rank has been applied to many web searches, but it cannot be directly applied to retrieval scientific research projects. In scientific research project query, people are not only concerned about the name of the project, but also the digital information and side-information, such as duration, achievements, funding amount of this project. Howerver, the existing learning to rank methods ignore the side-information of scientific research projects. Therefore, we propose a Side-information Pointwise Ranking model (SIPR) for scientific research project query based on deep language model, click model and learning to rank. First, we use the deep language model to extract the semantic information of text, and design a relevance calculation model to extract features of side-information, then we merge the above two features. After that we use the click model to eliminate position bias, and get a ranking score through pointwise DNN. Finally, we can get the query results ordered by these scores. Experiments on real scientific research projects dataset demonstrate that our model can achieve better performance. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Semantics

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：