检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yang, Dongjie Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China

Large Language Models (LLMs) have shown the impressive capability of answering questions in a wide range of scenarios. However, when LLMs face different types of questions, it is worth exploring whether LLMs are aware that some questions have limited answers and need to respond more deterministically but some do not. We refer to this as question awareness of LLMs. The lack of question awareness in LLMs leads to two phenomena that LLMs are: (1) too casual to answer non-open-ended questions or (2) too boring to answer open-ended questions. In this paper, we first evaluate the question awareness in LLMs. The experimental results show that LLMs have the issues of lacking awareness of questions in certain domains, e.g. factual knowledge, resulting in hallucinations during the generation. To mitigate these, we propose a method called Question Awareness Temperature Sampling (QuATS). This method enhances the question awareness of LLMs by adaptively adjusting the output distributions based on question features. The automatic adjustment in QuATS eliminates the need for manual temperature tuning in text generation and consistently improves model performance in various benchmarks. Copyright © 2024, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Multiuser Communication Aided by Movable Antenna 24

Multiuser Communication Aided by Movable Antenna

引用

24th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2023

作者： Zhu, Lipeng Ma, Wenyan Ning, Boyu Zhang, Rui University of Electronic Science and Technology of China National Key Laboratory of Science and Technology on Communications 611731 China The Chinese University of HongKong Shenzhen Research Institute of Big Data Shenzhen518172 China National University of Singapore Department of Electrical and Computer Engineering Singapore117583 Singapore

ISBN: (纸本)9781665496261

This paper investigates the multiuser communication aided by movable antenna (MA) via antenna position optimization, where the uplink transmission from multiple user terminals (UTs) each equipped with a single MA to a base station (BS) with a fixed-position antenna (FPA) array is considered. Specifically, we formulate an optimization problem for minimizing the total transmit power of UTs, subject to a minimum-achievable-rate requirement for each UT, where the positions of MAs and the transmit powers of UTs, as well as the receive combining matrix at the BS are jointly optimized. To solve this non-convex optimization problem, we first express the combining matrix of the BS and the total transmit power of UTs as a function of the MAs' position vectors, which are then optimized by using the gradient descent method in an iterative manner. Simulation results demonstrate that compared to conventional FPA systems, the proposed MA-enhanced multiple access systems can significantly decrease the total transmit power of UTs by moving antennas within small regions of several-wavelength size. © 2023 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Federated Causally Invariant Feature Learning 39

Federated Causally Invariant Feature Learning

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Guo, Xianjie Yu, Kui Cui, Lizhen Yu, Han Li, Xiaoxiao School of Computer Science and Information Engineering Hefei University of Technology China Key Laboratory of Knowledge Engineering with Big Data of Ministry of Education China School of Software Shandong University China College of Computing and Data Science Nanyang Technological University Singapore Department of Electrical and Computer Engineering The University of British Columbia Canada Vector Institute Canada

ISBN: (纸本)157735897X

Federated feature selection (FFS) is a promising field for selecting informative features while preserving data privacy in federated learning (FL) settings. Existing FFS methods focus on capturing the correlations between features and labels. They struggle to achieve satisfactory performance in the face of data distribution heterogeneity among FL clients, and cannot address the out-of-distribution (OOD) problem that arises when a significant portion of clients do not actively participate in FL training. To address these limitations, we propose Federated Causally Invariant Feature Learning (FedCIFL), a novel approach for learning causally invariant features in a privacy-preserving manner. We design a sample reweighting strategy to eliminate spurious correlations introduced by selection bias and iteratively estimate the federated causal effect between each feature and the labels (with the remaining features initially treated as confounders). By iteratively refining the confounding feature set to identify the true confounders, FedCIFL mitigates the impact of limited local data on the accuracy of federated causal effect estimation. Theoretical analysis proves the correctness of FedCIFL under reasonable assumptions. Extensive experiments on synthetic and real-world datasets demonstrate the superiority of FedCIFL against eight state-of-the-art baselines, beating the best-performing approach by 3.19%, 9.07% and 2.65% in terms of average test Accuracy, RMSE and F1 score, respectively. It is a first-of-its-kind FFS approach capable of handling Non-IID and OOD data simultaneously. The source code is available at https://***/Xianjie-Guo/FedCIFL. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Spatial Consistency and Feature Diversity Regularization in Transfer Learning for Fine-Grained Visual Categorization

Spatial Consistency and Feature Diversity Regularization in ...

引用

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Dai, Zhigang Chen, Junying Mian, Ajmal South China University of Technology Key Laboratory of Big Data and Intelligent Robot Ministry of Education School of Software Engineering Guangzhou China The University of Western Australia Department of Computer Science Perth Australia

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Fine-grained visual categorization is challenged by limited training data by localizing discriminative regions and learning diverse features. We propose an effective regularization method that simultaneously imposes spatial consistency and feature diversity on CNN feature maps from a unified perspective. The former guides different feature map channels to concentrate collaboratively on the discriminative areas while the latter ensures that the feature maps are diverse. The proposed method does not require additional supervision, and leverages the covariance matrix of multi-channel feature maps to regularize the loss at the last convolutional layer where the semantic information is the richest. This allows the influence to be backpropagated to update all convolutional layers. We perform experiments using four network architectures for transfer learning from two source domains to three target domains, and demonstrate that our regularization method improves accuracy in all different settings. The proposed regularization method achieves state-of-the-art performance on CUB-200-2011, Stanford-Cars, and Stanford-Dogs datasets with 89.8%, 94.6%, and 88.5% accuracy, respectively. © 2022 IEEE.

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

Chinese Lexical Simplification

引用

IEEE/ACM Transactions on Audio Speech and Language Processing 2021年 29卷 1819-1828页

作者： Qiang, Jipeng Lu, Xinyu Li, Yun Yuan, Yunhao Wu, Xindong Department of Computer Science Yangzhou China Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology Hefei China

Lexical simplification has attracted much attention in many languages, which is the process of replacing complex words in a given sentence with simpler alternatives of equivalent meaning. Although the richness of vocabulary in Chinese makes the text very difficult to read for children and non-native speakers, there is no research work for the Chinese lexical simplification (CLS) task. To circumvent difficulties in acquiring annotations, we manually create the first benchmark dataset for CLS, which can be used for evaluating the lexical simplification systems automatically. To acquire a more thorough comparison, we present five different types of methods as baselines to generate substitute candidates for the complex word that includes synonym-based approach, word embedding-based approach, BERT-based approach, sememe-based approach, and a hybrid approach. Finally, we design the experimental evaluation of these baselines and discuss their advantages and disadvantages. To our best knowledge, this is the first study for CLS task. © 2014 IEEE.

关键词： BERT Lexical simplification pretrained language model unsupervised

来源：评论

学校读者我要写书评

暂无评论

Cultural-Aware AI Model for Emotion Recognition

Cultural-Aware AI Model for Emotion Recognition

引用

Iranian Machine Vision and Image Processing (MVIP)

作者： Mehrdad Baradaran Payam Zohari Abtin Mahyar Hossein Motamednia Dara Rahmati Saeid Gorgin Department of Computer and Data Sciences Shahid Beheshti University Tehran Iran Department of Computer Engineering Khaje Nasir University Of Technology Tehran Iran High Performance Computing Laboratory School of Computer Science Institute for Research in Fundamental Sciences Tehran Iran Faculty of Computer Science and Engineering Shahid Beheshti University Tehran Iran Department of Computer Engineering Chosun University Gwangju South Korea

Emotion AI is a research domain that aims to understand human emotions from visual or textual data. However, existing methods often ignore the influence of cultural diversity on emotional interpretation. In this paper, we propose a multimodal deep learning model that integrates cultural awareness into emotion recognition. Our model uses images as the primary data source and comments from individuals across different regions as the secondary data source. Our results show that our model achieves robust performance across various scenarios. Our contribution is to introduce a novel fusion approach that bridges cultural gaps and fosters a more nuanced understanding of emotions. Due to the best of our knowledge, few works are using this approach, for Emotion AI, combining different types of data sources and models. We evaluate our model on the ArtELingo dataset, which contains image-comment pairs with Chinese, Arabic, and English annotations. The experimental results in the evaluation phase demonstrate an impressive 80% recognition accuracy for the model that merges image-text features.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quality Assessment of Electrocardiogram Signals Using Contrastive Learning 13

Quality Assessment of Electrocardiogram Signals Using Contra...

引用

13th International Conference on Information Technology in Medicine and Education, ITME 2023

作者： Zhong, Meiping Li, Zuoyong Wang, ChuanSheng Huang, Jiayan Zhao, WanQi Fan, Haoyi College of Computer and Big Data Fuzhou University Fuzhou350108 China College of Computer and Control Engineering Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou350121 China Polytechnic University of Catalonia Department of Automatic Control Technical Barcelona08034 Spain New Engineering Industry College Putian University Putian351100 China School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou450001 China

ISBN: (纸本)9798350319156

Quality assessment of electrocardiogram (ECG) signals holds significant importance in reducing the high-frequency false alarms in automated arrhythmia diagnosis. Existing quality assessment methods primarily rely on empirical threshold setting or the calculation of relevant statistical values to formulate decision rules. However, the thresholds set in this manner are typically based on experience and knowledge, resulting in decision rules that lack flexibility and struggle to adapt to changes in the dataset. To address this issue, many researchers have turned to deep learning algorithms for ECG signal quality assessment. Nevertheless, most existing deep learning methods usually require large-scale and labeled ECG data for training, whose acquiring is typically challenging. Therefore, this paper proposes an efficient method for ECG signal quality assessment. First, we use a contrast learning framework to construct sample pairs through multilevel data augmentation. Second, a densely connected convolutional network (DenseNet) is used to improve the model's ability of extracting local features in ECG signals, and a Squeeze-and-Excitation attention module is introduced to make the model pay more attention to critical features. Finally, the feature representation is learned by minimizing the contextual contrast loss to bring similar samples closer and push dissimilar samples farther away. In this way, we can utilize the contrastive learning framework to extract temporal representations from unlabeled data and transfer them to downstream ECG signal quality assessment tasks. Extensive experiments on the Physionet/CinC Challenge 2011 dataset demonstrate that our approach outperforms most existing quality assessment methods. © 2023 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Learning with Multiple Classifier Aggregation

SSRN

引用

SSRN 2024年

作者： Zheng, Shaifeng Zhu, Qingling Lin, Qiuzhen Liu, Songbai Wong, Ka-Chun Li, Jianqiang College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Computer Science City University of Hong Kong Hong Kong

Personalized federated learning (PFL) has garnered attention due to its capability to address statistical heterogeneity among clients. Typically, prevailing PFL methods aggregate a single global model for personalization, which may be inadequate for clients with diverse data distributions. Furthermore, in the local update, each private dataset is used to optimize the model independently, which increases the risk of overfitting the current data distribution and losing previously acquired knowledge, resulting in knowledge forgetting. In this study, personalized federated learning with multiple classifier aggregation is proposed. The method involves splitting the client model into its head and base, then optimizing them respectively using an alternating optimization strategy that first optimizes the head and then the base. Initially, to address the suboptimal model problem, the proposed approach aggregates multiple classifiers using data distribution and employs knowledge distillation to impart positive and negative classifier knowledge for learning the most suitable personalized model head. Additionally, to mitigate knowledge forgetting, a learnable personalization layer is introduced, and hidden loss is utilized to learn the knowledge of the global base and prevent overfitting of the model base. Empirical results demonstrate that the proposed method achieves competitive performance across various benchmarks, outperforming the majority of state-of-the-art PFL algorithms. The source code is publicly available at \href{https://***/xiaye-maker/FedMCA}{https://***/xiaye-maker/FedMCA} © 2024, The Authors. All rights reserved.

关键词： Aggregates

来源：评论

学校读者我要写书评

暂无评论

Learning a Typhoon Bayesian Network Structure from Natural Language Reports 5th

Learning a Typhoon Bayesian Network Structure from Natural...

引用

5th IFIP TC 12 International Conference on Intelligence Science, ICIS 2022

作者： Yao, Zhangrui Chen, Junhan Pan, Yinghui Zeng, Yifeng Ma, Biyang Ming, Zhong Department of Automation and Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision-Making Xiamen University Xiamen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Computer and Information Sciences Northumbria University Newcastle upon Tyne United Kingdom School of Computer Science and Engineering Minnan Normal University Zhangzhou China

ISBN: (纸本)9783031149023

Given the huge toll caused by natural disasters, it is critically important to develop an effective disaster management and emergency response technique. In this article, we investigate relationships between typhoon-related variables and emergency response from natural language (NL) reports. A major challenge is to exploit typhoon state information for typhoon contingency plan generation, especially from unstructured text data based on NL input. To tackle this issue, we propose a novel framework for learning typhoon Bayesian network structures (FLTB), which can extract typhoon state information from unstructured NL, mine inter-information causal relationships and then generate Bayesian networks. We first extract information about typhoon states through NL processing (NLP) techniques, and then analyze typhoon reports by designing heuristic rules to identify causal relationships between states. We leverage these features to improve the learned structures and provide user-interaction mechanisms to finalize Bayesian networks. We evaluate the performance of our framework on real-world typhoon datasets and develop the Bayesian networks based typhoon emergency response systems. © 2022, IFIP International Federation for Information Processing.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

data Preprocessing Technology in Network Traffic Anomaly Detection

Data Preprocessing Technology in Network Traffic Anomaly Det...

引用

作者： Duan, Xueyuan Fu, Yu Wang, Kun Department of Information Security Naval University of Engineering Wuhan430033 China College of Computer and Information Technology Xinyang Normal University Xinyang464000 China Henan Key Laboratory of Analysis and Applications of Education Big Data Xinyang464000 China School of Mathematics and Information Engineering Xinyang Vocational and Technical College Xinyang464000 China

computer network plays a very important role in today’s world. With the development of network technology and the increasing popularity of network topology, network management is facing huge challenges. Among them, finding network traffic anomalies is one of the most important tasks in network monitoring, and is an important technology in network intrusion, security monitoring, and performance maintenance. This paper aims to study data preprocessing techniques in network traffic anomaly detection. This paper firstly introduces the network traffic measurement characteristics completely, and then selects and applies the data preprocessing algorithm, constructs a complete data preprocessing framework, and conducts experiments for the abnormal detection of network multi-dimensional characteristic traffic and the abnormal detection of unit-level characteristic traffic. The superiority of the data preprocessing technology in this paper, by reducing the data, determines the data preprocessing threshold of this paper to ensure that the data preprocessing is maximized. Experiments show that the data preprocessing technology constructed in this paper has about 20% more data filtering than traditional data filtering, which shortens the amount of detection data. The threshold is around 0.6, and data preprocessing can maximize the reduction of data without destroying the integrity of the attacked data. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： data mining

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：