检索结果-内蒙古大学图书馆

Causal Representation Enhances Cross-Domain Named Entity Recognition in Large Language Models

computers, Materials & Continua 2025年第5期83卷 2809-2828页

作者： Jiahao Wu Jinzhong Xu Xiaoming Liu Guan Yang Jie Liu School of Artificial Intelligence Zhongyuan University of TechnologyZhengzhou450007China School of Computer Science Zhongyuan University of TechnologyZhengzhou450007China Zhengzhou Key Laboratory of Text Processing and Image Understanding Zhengzhou450007China School of Information Science and Technology North China University of TechnologyBeijing100144China

Large language models cross-domain named entity recognition task in the face of the scarcity of large language labeled data in a specific domain,due to the entity bias arising from the variation of entity information between different domains,which makes large language models prone to spurious correlations problems when dealing with specific domains and *** order to solve this problem,this paper proposes a cross-domain named entity recognition method based on causal graph structure enhancement,which captures the cross-domain invariant causal structural representations between feature representations of text sequences and annotation sequences by establishing a causal learning and intervention module,so as to improve the utilization of causal structural features by the large languagemodels in the target domains,and thus effectively alleviate the false entity bias triggered by the false relevance problem;meanwhile,through the semantic feature fusion module,the semantic information of the source and target domains is effectively *** results show an improvement of 2.47%and 4.12%in the political and medical domains,respectively,compared with the benchmark model,and an excellent performance in small-sample scenarios,which proves the effectiveness of causal graph structural enhancement in improving the accuracy of cross-domain entity recognition and reducing false correlations.

关键词： Large language model entity bias causal graph structure

来源：评论

学校读者我要写书评

暂无评论

A Tutorial on Federated Learning from Theory to Practice:Foundations,Software Frameworks,Exemplary Use Cases,and Selected Trends

引用

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 824-850页

作者： M.Victoria Luzón Nuria Rodríguez-Barroso Alberto Argente-Garrido Daniel Jiménez-López Jose M.Moyano Javier Del Ser Weiping Ding Francisco Herrera Department of Software Engineering Andalusian Research Institute in Data Science and Computational Intelligence(DaSCI)University of GranadaGranada 18071Spain Department of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence(DaSCI)University of GranadaGranada 18071Spain Department of Communications Engineering University of the Basque Country(UPV/EHU)and also with TECNALIABasque Research&Technology Alliance(BRTA)Spain School of Information Science and Technology Nantong UniversityNantong 226019China

When data privacy is imposed as a necessity,Federated learning(FL)emerges as a relevant artificial intelligence field for developing machine learning(ML)models in a distributed and decentralized *** allows ML models to be trained on local devices without any need for centralized data transfer,thereby reducing both the exposure of sensitive data and the possibility of data interception by malicious third *** paradigm has gained momentum in the last few years,spurred by the plethora of real-world applications that have leveraged its ability to improve the efficiency of distributed learning and to accommodate numerous participants with their data *** virtue of FL,models can be learned from all such distributed data sources while preserving data *** aim of this paper is to provide a practical tutorial on FL,including a short methodology and a systematic analysis of existing software ***,our tutorial provides exemplary cases of study from three complementary perspectives:i)Foundations of FL,describing the main components of FL,from key elements to FL categories;ii)Implementation guidelines and exemplary cases of study,by systematically examining the functionalities provided by existing software frameworks for FL deployment,devising a methodology to design a FL scenario,and providing exemplary cases of study with source code for different ML approaches;and iii)Trends,shortly reviewing a non-exhaustive list of research directions that are under active investigation in the current FL *** ultimate purpose of this work is to establish itself as a referential work for researchers,developers,and data scientists willing to explore the capabilities of FL in practical applications.

关键词： data privacy distributed machine learning federated learning software frameworks

来源：评论

学校读者我要写书评

暂无评论

LGDF-Net: Local and Global Feature Based Dual-Branch Fusion Networks for Deepfake Detection

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第6期35卷 5489-5500页

作者： Long, Min Liu, Zhenyu Zhang, Le-Bing Peng, Fei Guangzhou University School of Electronics and Communication Engineering Guangdong Guangzhou510006 China Changsha University of Science and Technology School of Computer and Communication Engineering Changsha410114 China Huaihua University School of Computer and Artificial Intelligence Huaihua418000 China Guangzhou University School of Artificial Intelligence Guangdong Guangzhou510006 China

With the rapid development of Deepfake technology, social security is facing great challenges. Although numerous Deepfake detection algorithms based on traditional CNN frameworks perform well on specific datasets, they still suffer from overfitting due to an over-reliance on localized artifact information. This limitation leads to degraded detection performance across diverse datasets. To address this issue, this study proposes a dual-branch fusion network called LGDF-Net. LGDF-Net uses a dual-branch structure to process the local artifact features and global texture features generated by Deepfake separately, preserving their unique characteristics. Specifically, the local compression branch utilizes a specially designed local compression module (LCM) that allows the network to focus more accurately on key regions of localized artifacts in Deepfake faces. The global expansion branch enhances the analysis of the global facial context through a global expansion module (GEM), which captures image context information and subtle texture features more comprehensively. Additionally, the proposed multi-scale feature extraction module (MSFE) delves into image features at various scales, enriching the extraction of detailed information. Finally, the multi-level feature fusion strategy (MLFF) improves the integration of local and global features through multiple layers, enabling the network to learn the intrinsic connections between these two types of features. A series of experimental validations demonstrate that the proposed scheme outperforms many existing detection networks in terms of accuracy and generalization ability. © 1991-2012 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Malayalam Fake News Detection Using Optimized Convolutional Neural Network (OPCNN) 11

Malayalam Fake News Detection Using Optimized Convolutional ...

引用

11th IEEE International Conference on Advances in Computing and Communications, ICACC 2024

作者： Mohan, Aiswarya Iqbal, Nafla Mashpher, Manaal Rajagiri School of Engineering and Technology Department of Artificial Intelligence and Data Science Kakkanad India

ISBN: (纸本)9798350379136

These days, a range of issues are being caused by fake news, including satirical pieces, fake news, and intentional government propaganda. Because of the blathering social media discourse, the idea of "fake news"has recently evolved. Wide-ranging consequences of fake news dissemination include the development of distorted opinions and the tampering of election outcomes to benefit specific politicians. Spammers also use captivating news headlines to entice readers to click on their advertisements. These days, it can be quite difficult to tell if the news we hear is accurate. There aren't many methods for assessing authenticity, and the ones that are accessible are all difficult and beyond the capabilities of the average person. A fact-checking platform that gives us that chance is desperately needed. Deep Learning (DL) approaches are suited for more accurately and efficiently detecting false news because of their recent accomplishments in difficult natural language processing tasks. The suggested approach is a multi-layered, optimal CNN model for detecting fake news. The OPCNN and Word embedding are optimized for feature extraction using the hyperopt optimization method in order to produce highly accurate results. In this study, we generated word embeddings using the FastText technique. The purpose of the model is to identify news stories published in Malayalam that are either false or misleading. The model is trained on 80% of a newly compiled Malayalam dataset consisting of news articles from various online sources having 11,686 news items with 5843 false and real news entries apiece and then evaluated on the remaining 20%. The evaluation's findings show that the suggested model works better than current methods and has a high degree of accuracy when it comes to identifying false information in Malayalam. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Multiscale Complementary Semantic Enhancement Network for Welding Seam X-ray Image Defect Detection 7

Multiscale Complementary Semantic Enhancement Network for We...

引用

7th International Symposium on Autonomous Systems, ISAS 2024

作者： Liu, Weipeng Wang, Yuheng Chen, Haiyong Hebei University of Technology School of Artificial Intelligence and Data Science Tianjin300132 China

ISBN: (纸本)9798350363173

The core challenge in the analysis of welding seam X-ray images is the problem of multiscale defects, where defects can range in size and shape from tiny pores to larger unpenetrated areas. However, the current methods have limitations, such as information loss during feature extraction and inadequate scale adjustment strategies during feature fusion, making it difficult for models to capture complex semantic information and retain key details effectively. In this paper, we propose a Multiscale Complementary Semantic Enhancement Network (MCSEN), which includes a Multi-level Semantic Enhancement (MSE) module and a Multi-level Feature Complementary Aggregation (MFCA) module. The MSE module improves multiscale feature learning through graph convolution-guided feature aggregation, effectively mitigating the problem of information loss and enhancing features' distinguishability and semantic richness. The MFCA module resolves the issues of scale inconsistency and semantic discontinuity in feature fusion by adaptively generating fusion weights and finely adjusting feature allocation. Comprehensive experiments show that MCSEN achieves an overall average precision of 91.9%, significantly higher than other models. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Multi-level Attention-enhanced Learning for Fine-Grained Visual Classification 24

Multi-level Attention-enhanced Learning for Fine-Grained Vis...

引用

8th International Conference on computer science and artificial intelligence, CSAI 2024

作者： Ding, Kaifeng Yang, Caolin Yang, Chengzhuan Zheng, Zhonglong School of Computer Science and Technology School of Artificial Intelligence Zhejiang Normal University ZheJiang Jinhua China

ISBN: (纸本)9798400718182

Due to significant intra-class variations and subtle inter-class differences, fine-grained images often pose challenges. In this paper, we propose a multi-level attention-enhanced network framework to address this issue. First, we employ convolutional features to crop the original images to focus on the main part and mitigate the interference of backgrounds on classification. Second, we design a scale-adaptive local discriminative region generation module based on the main part’s images, effectively selecting locally detailed and rich image patches. It is worth noting that our proposed method only utilizes image-level labels. Finally, we extensively tested our method on three benchmark datasets, including the CUB-200-2011, Stanford Cars, and FGVC Aircraft. The experimental results demonstrate that our method achieves comparable or better classification performance than previous state-of-the-art fine-grained visual classification methods. © 2024 Copyright held by the owner/author(s).

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Diffusion Model for Traffic data Imputation

引用

IEEE/CAA Journal of Automatica Sinica 2025年第3期12卷 606-617页

作者： Bo Lu Qinghai Miao Yahui Liu Tariku Sinshaw Tamir Hongxia Zhao Xiqiao Zhang Yisheng Lv Fei-Yue Wang the School of Artificial Intelligence University of Chinese Academy of Sciences Baidu Inc. IEEE the State Key Laboratory for Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Meituan Guangdong University of Technology the Department of Transportation Engineering School of Transportation Science and Technology Harbin Institute of Technology

Imputation of missing data has long been an important topic and an essential application for intelligent transportation systems(ITS) in the real world. As a state-of-the-art generative model, the diffusion model has proven highly successful in image generation, speech generation, time series modelling *** now opens a new avenue for traffic data imputation. In this paper, we propose a conditional diffusion model, called the implicit-explicit diffusion model, for traffic data imputation. This model exploits both the implicit and explicit feature of the data simultaneously. More specifically, we design two types of feature extraction modules, one to capture the implicit dependencies hidden in the raw data at multiple time scales and the other to obtain the long-term temporal dependencies of the time series. This approach not only inherits the advantages of the diffusion model for estimating missing data, but also takes into account the multiscale correlation inherent in traffic data. To illustrate the performance of the model, extensive experiments are conducted on three real-world time series datasets using different missing *** experimental results demonstrate that the model improves imputation accuracy and generalization capability.

关键词： data imputation diffusion model implicit feature time series traffic data

来源：评论

学校读者我要写书评

暂无评论

CaDRL: Document-level Relation Extraction via Context-aware Differentiable Rule Learning 31

CaDRL: Document-level Relation Extraction via Context-aware ...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Zhang, Kunli Wu, Pengcheng Yu, Bohan Wu, Kejun Zheng, Aoze Huang, Xiyang Zhu, Chenkang Peng, Min Zan, Hongying Song, Yu School of Computer Science and Artificial Intelligence Zhengzhou University China School of Computer Science Wuhan University China

ISBN: (纸本)9798891761964

Document-level Relation Extraction (DocRE) aims to extract relations from documents. Compared with sentence-level relation extraction, it is necessary to extract long-distance dependencies. Existing methods enhance the output of trained DocRE models either by learning logical rules or by extracting rules from annotated data and then injecting them into the model. However, these approaches can result in suboptimal performance due to incorrect rule set constraints. To mitigate this issue, we propose Context-aware Differentiable Rule Learning or CaDRL for short, a novel differentiable rule-based framework that learns the doc-specific logical rule to avoid generating suboptimal constraints. Specifically, we utilize Transformer-based relation attention to encode document and relation information, thereby learning the contextual information of the relation. We employ a sequence-generated differentiable rule decoder to generate relational probabilistic logic rules at each reasoning step. We also introduce a parameter sharing training mechanism in CaDRL to reconcile the DocRE model and the rule learning module. Extensive experimental results on three DocRE datasets demonstrate that CaDRL outperforms existing rule-based frameworks, significantly improving DocRE performance and making predictions more interpretable and logical. © 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

Personalized Music Recommendation: A Comparative Study of Machine Learning and Deep Learning Approaches 11

Personalized Music Recommendation: A Comparative Study of Ma...

引用

11th IEEE International Conference on Advances in Computing and Communications, ICACC 2024

作者： Iqbal, Nafla Mohan, Aiswarya Syjo, Ann Rose Rajagiri School of Engineering and Technology Dept of Artificial Intelligence and Data Science Kakkanad India

ISBN: (纸本)9798350379136

The rapid advancement of music playback technology, particularly within mobile platforms, has fundamentally transformed user engagement with music. Despite significant improvements in music retrieval techniques over the past decade, the evolution of music recommendation systems remains in its early stages. With users having access to extensive online music libraries, the task of selecting preferred tracks from an overwhelming array of options presents a considerable challenge. Individual musical tastes vary widely, and the influx of new users and music necessitates a system that can adapt *** music recommendation systems face the dual challenge of managing vast amounts of data while delivering accurate results, making them resource-intensive. However, the high precision of these models drives their increasing application in commercial settings. This paper proposes a framework aimed at enhancing recommendation accuracy by tailoring suggestions to align more closely with user preferences.A comprehensive analysis of traditional and advanced music recommendation methodologies is presented, focusing on two user-centric approaches: user preference and emotion-based metrics. These methodologies are critically compared, leveraging the Million Song dataset (MSD) for training the recommendation system. Additionally, an Android application has been developed to collect empirical data on user experiences, facilitating a deeper understanding of user interactions and satisfaction with the recommendation framework. This research aims to improve user experience in music discovery by providing more relevant and personalized recommendations. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Residential Energy Scheduling With Solar Energy Based on Dyna Adaptive Dynamic Programming

引用

IEEE/CAA Journal of Automatica Sinica 2025年第2期12卷 403-413页

作者： Kang Xiong Qinglai Wei Hongyang Li the Institute of Systems Engineering Macau University of Science and Technology IEEE the State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences the School of Artificial Intelligence University of Chinese Academy of Sciences

Learning-based methods have become mainstream for solving residential energy scheduling problems. In order to improve the learning efficiency of existing methods and increase the utilization of renewable energy, we propose the Dyna actiondependent heuristic dynamic programming(Dyna-ADHDP)method, which incorporates the ideas of learning and planning from the Dyna framework in action-dependent heuristic dynamic programming. This method defines a continuous action space for precise control of an energy storage system and allows online optimization of algorithm performance during the real-time operation of the residential energy model. Meanwhile, the target network is introduced during the training process to make the training smoother and more efficient. We conducted experimental comparisons with the benchmark method using simulated and real data to verify its applicability and performance. The results confirm the method's excellent performance and generalization capabilities, as well as its excellence in increasing renewable energy utilization and extending equipment life.

关键词： Adaptive dynamic programming (ADP) dynamic residential scenarios optimal residential energy management smart grid

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：