检索结果-内蒙古大学图书馆

IEEE Conference on Wireless Communications and Networking

作者： Guanyu Zhang Jiaqi Zou Songlin Sun School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education China

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

This paper considers a joint design for communication beamforming matrices and radar waveform in a scenario where a multiple-input multiple-output (MIMO) radar and a MIMO communication system coexist. We propose a joint optimizing method to maximize the sum rate by designing the communication beamforming matrices and the radar waveform. We give consideration to power constraints for both radar and communication system. In order to guarantee the radar performance, we also consider the similarity constraint of the radar waveform. This paper formulates two convex optimization problems and proposes an alternating iterative algorithm. Finally, the simulation results verify that the proposed algorithm can effectively raise the sum rate.

关键词： Array signal processing MIMO radar Simulation Optimization methods Radar Interference Convex functions

来源：评论

学校读者我要写书评

暂无评论

Adversarial Residual Variational Graph Autoencoder with Batch Normalization 6

Adversarial Residual Variational Graph Autoencoder with Batc...

引用

6th IEEE International Conference on Data Science in Cyberspace, DSC 2021

作者： Liao, Qisheng Wu, Xu Xie, Xiaqing Wu, Jingchen Qiu, Lirong Sun, Lijuan Beijing University Of Posts And Telecommunications Key Laboratory Of Trustworthy Distributed Computing And Service Ministry Of Education Beijing China

ISBN: (纸本)9781665418157

The variational graph autoencoder (VGAE), a framework for unsupervised learning on graph-structured data, has captured more attention recently in graph embedding area. However, it has been faced up with the challenge of KL vanishing, which will converge to local optimum and make the graph embedding unavailable for downstream tasks like link prediction. This paper proposes a novel variational graph autoencoder framework to achieve more effective graph embedding. Firstly, we introduce batch normalization to make sure the KL distribution consistent with the whole dataset by keeping its expectation positive, thus avoiding posteriori collapse. In addition, we invite residual connection and adversarial network to simultaneously embed the topology information and content information into graph representation stably, enhancing the expressive ability of latent vector. Finally, link prediction experiments on three citation datasets demonstrate that the AUC scores of our algorithm are higher than 92% and the average accuracies are higher than 93%, which is competitive comparing with the state-of-the-art variational graph autoencoders. © 2021 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Sensitive Image Information Recognition Model of Network Community based on Content Text 6

Sensitive Image Information Recognition Model of Network Com...

引用

6th IEEE International Conference on Data Science in Cyberspace, DSC 2021

作者： Gao, Li Wu, Xu Wu, Jingchen Xie, Xiaqing Qiu, Lirong Sun, Lijuan Beijing University Of Posts And Telecommunications Key Laboratory Of Trustworthy Distributed Computing And Service Ministry Of Education Beijing China

ISBN: (纸本)9781665418157

With the advent of the multimedia era and the age of picture-reading, the recognition effect of sensitive content of image data has become the key to maintain the information security of network communities. At present, the image classification and recognition technology for sensitive images in network communities cannot obtain the semantic content of images, and it is difficult to combine the image information with the knowledge in network communities, resulting in low recognition accuracy and poor interpretability, and it is difficult to trace the transmission and fermentation of image information in network communities. To solve this problem, this paper proposes a sensitive image information recognition model of network community based on content text by using image caption technology. Through the text description of the image content of the network community, and the integration of a large number of network community text knowledge, the model can finally identify the images containing sensitive content more accurately and more understandable, and the transmission of image information on the network can be traced through the content text. In this paper, MSCOCO(Microsoft Common Objects in Context) dataset and sensitive image self-made dataset of network community are used as the training set. The experimental results show that the method presented in this paper is significantly better than the model based on image classification task in terms of accuracy and traceability of image sensitive information recognition results, which proves the feasibility and effectiveness of sensitive image information recognition in network communities based on content text. © 2021 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

EHealth: A Chinese Biomedical Language Model Built via Multi-Level Text Discrimination

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 908-921页

作者： Quan Wang Songtai Dai Benfeng Xu Yajuan Lyu Hua Wu Haifeng Wang MOE Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications Beijing China Baidu Inc. Beijing China School of Information Science and Technology University of Science and Technology of China Hefei China

Pre-trained language models (PLMs) have recently revolutionized the field of natural language processing, impacting not only the general domain but also the biomedical domain. Most previous studies on constructing biomedical PLMs relied simply on domain adaptation and focused mainly on English. This work introduces eHealth, a compact, encoder-based Chinese biomedical PLM that can be fine-tuned in a customized manner to effectively handle various Chinese biomedical language understanding tasks. Rather than relying on domain adaptation, eHealth is built from scratch using a novel pre-training framework. This framework trains eHealth as a discriminator through token- and sequence-level discrimination. Token-level discrimination detects corrupted input tokens and recovers their original forms from plausible candidates, while sequence-level discrimination further distinguishes corruptions of the same original sequence from those of others. As a result, eHealth can learn language semantics at both token and sequence levels. Moreover, eHealth is trained entirely from scratch with a newly constructed in-domain vocabulary, which may help improve tokenization and understanding of biomedical text. Extensive experiments on 11 Chinese biomedical language understanding tasks of various forms verify the effectiveness and superiority of eHealth. The pre-trained model as well as the code have been released to the public.

关键词： Biological system modeling Electronic healthcare Adaptation models Vocabulary Encoding Generators Bidirectional control Training Computational modeling Speech processing

来源：评论

学校读者我要写书评

暂无评论

MTP: A Minimal Task Perturbation Framework for Mitigating Poisoning Attacks in Federated Learning

MTP: A Minimal Task Perturbation Framework for Mitigating Po...

引用

Image Processing, Computer Vision and Machine Learning (ICICML), International Conference on

作者： Weiqiang Jiang Tianyu Su Guangtao Wang Dongqi Han China Mobile Group Co. Ltd Beijing China Key Laboratory of Trustworthy Distributed Computing and Service (MoE) Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798350355413

ISBN: (纸本)9798350355420

Federated Learning achieves privacy protection by allowing different participants to jointly train models. However, this characteristic also makes Federated Learning susceptible to data poisoning attacks. Many existing defense methods can successfully defend against various data poisoning attacks, but they are often only effective against one of the independent and identically distributed (IID) or non-independent and identically distributed (non-IID) scenarios. In this paper, we propose a novel minimal task perturbation framework named MTP for mitigating data poisoning attacks in both IID and non-IID scenarios. To efficiently identify potential attackers, MTP utilizes a weight similarity ensemble mechanism based on four distance algorithms and clusters clients according to the fused weight similarity. Moreover, MTP uses a clipped weight aggregation to minimize the impact on the performance of main task. Experimental results show that the proposed MTP outperforms state-of-the-art methods in stability and security, and maintain higher accuracy of the main task.

关键词： Privacy Computer vision Federated learning Perturbation methods Image processing distributed databases Stability analysis Security Protection Detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Experimental demonstration of a quantum downstream access network in continuous variable quantum key distribution with a local local oscillator

引用

Photonics Research 2024年第6期12卷 1262-1273页

作者： DENGKE QI XIANGYU WANG ZHENGHUA LI JIAYU MA ZIYANG CHEN YUEMING LU SONG YU State Key Laboratory of Information Photonics and Optical Communications Beijing University of Posts and TelecommunicationsBeijing 100876China Key Laboratory of Trustworthy Distributed Computing and Service(MoE) Beijing University of Posts and TelecommunicationsBeijing 100876China State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronicsand Center for Quantum Information TechnologyPeking UniversityBeijing 100871China

Quantum networks provide opportunities and challenges across a range of intellectual and technical frontiers,including quantum computation,communication,and *** traditional communication networks,quantum networks utilize quantum bits rather than classical bits to store and transmit *** key distribution(QKD)relying on the principles of quantum mechanics is a key component in quantum networks and enables two parties to produce a shared random secret key,thereby ensuring the security of data *** this work,we propose a cost-effective quantum downstream access network structure in which each user can get their corresponding key information through terminal *** on this structure,we demonstrate the first four-end-users quantum downstream access network in continuous variable QKD with a local local *** contrast to point-to-point continuous variable QKD,the network architecture reevaluates the security of each user and accounts for it accordingly,and each user has a lower tolerance for excess noise as the overall network expands with more ***,the feasibility of the experiment is based on the analysis of the theoretical model,noise analysis,and multiple techniques such as the particle filter and adaptive equalization algorithm used to suppress excess *** results show that each user can get a low level of excess noise and can achieve secret key rates of 546 kbps,535 kbps,522.5 kbps,and 512.5 kbps under a transmission distance of 10 km,respectively,with the finite-size block of 1×10~*** not only verifies the good performance but also provides the foundation for the future multi-user quantum downstream access networks.

关键词： quantum oscillator local

来源：评论

学校读者我要写书评

暂无评论

Air-Decoding: Attribute Distribution Reconstruction for Decoding-Time Controllable Text Generation

arXiv

引用

arXiv 2023年

作者： Zhong, Tianqi Wang, Quan Han, Jingxuan Zhang, Yongdong Mao, Zhendong University of Science and Technology of China China MOE Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications China

Controllable text generation (CTG) aims to generate text with desired attributes, and decoding-time-based methods have shown promising performance on this task. However, in this paper, we identify the phenomenon of Attribute Collapse for the first time. It causes the fluency of generated text to rapidly decrease when the control strength exceeds a critical value, rendering the text completely unusable. This limitation hinders the effectiveness of decoding methods in achieving high levels of controllability. To address this problem, we propose a novel lightweight decoding framework named Air-Decoding. Its main idea is reconstructing the attribute distributions to balance the weights between attribute words and non-attribute words to generate more fluent text. Specifically, we train prefixes by prefix-tuning to obtain attribute distributions. Then we design a novel attribute distribution reconstruction method to balance the obtained distributions and use the reconstructed distributions to guide language models for generation, effectively avoiding the issue of Attribute Collapse. Experiments on multiple CTG tasks prove that our method achieves a new state-of-the-art control performance. Copyright © 2023, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Empowered Beam Management for Intelligent Reflecting Surface Assisted MmWave Networks

引用

China Communications 2020年第10期17卷 100-114页

作者： Chenglu Jia Hui Gao Na Chen Yuan He Key Lab of Trustworthy Distributed Computing and Service Beijing University of Posts and TelecommunicationsBeijing 100876China Nara Institute of Science and Technology Japan

Recently,intelligent reflecting surface(IRS)assisted mmWave networks are emerging,which bear the potential to address the blockage issue of the millimeter wave(mmWave)communication in a more cost-effective *** particular,IRS is built by passive and programmable electromagnetic elements that can manipulate the mmWave propagation channel into a more favorable condition that is free of blockage via judicious joint base station(BS)-IRS transmission ***,the coexistence of IRSs and mmWave BSs complicates the network architecture,and thus poses great challenges for efficient beam management(BM)that is one critical prerequisite for high performance mmWave *** this paper,we systematically evaluate the key issues and challenges of BM for IRS-assisted mmWave networks to bring insights into the future network ***,we carefully classify and discuss the extensibility and limitations of the existing BM of conventional mmWave towards the IRS-assisted new ***,we propose a novel machine learning empowered BM framework for IRS-assisted networks with representative showcases,which processes environmental and mobility awareness to achieve highly efficient BM with significantly reduced system ***,some interesting future directions are also suggested to inspire further researches.

关键词： mmWave networks IRS beam management machine learning

来源：评论

学校读者我要写书评

暂无评论

TCN-Log2Vec: A Comprehensive Log Anomaly Detection Framework based on Optimized Log Parsing and Temporal Convolutional Network

TCN-Log2Vec: A Comprehensive Log Anomaly Detection Framework...

引用

Consumer Electronics and Computer Engineering (ICCECE), 2021 IEEE International Conference on

作者： Zhe Jiang Yali Gao Jie Yuan Kaiguo Yuan Xiaoyong Li Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education College of Cyberspace Security Beijing University of Posts and Telecommunications Beijing China

Logs that record execution information and system status, are useful for anomaly detection. Traditionally, developers manually checked logs through keyword search or rule matching. However, as the number of logs increases, this approach becomes unrealistic. More and more methods of log anomaly detection based on machine learning and deep learning have been proposed. In order to detect log anomalies accurately and effectively, this paper proposes a comprehensive framework, namely TCN-Log2Vec. Based on Drain, a prevalent and effective method to extract the log templates from the original logs, TCN-Log2Vec has done some optimization work in log parsing. It also captures sequence information, quantitative information, and semantic information from the original log. Meanwhile, it designs the anomaly detection module based on TCN (Temporal Convolutional Network) to achieve parallel processing. Our log parsing method achieves 99% accuracy on HDFS datasets and 94% accuracy on BGL datasets. We compare our anomaly detection framework with other advanced methods including DeepLog, LogAnomaly, and LogRobust, the experiment results show that our model has better performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing robustness of graph neural networks on social media with explainable inverse reinforcement learning 24

Enhancing robustness of graph neural networks on social medi...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Yuefei Lyu Chaozhuo Li Sihong Xie Xi Zhang Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education Beijing University of Posts and Telecommunications China Artificial Intelligence Thrust The Hong Kong University of Science and Technology (Guangzhou) China

ISBN: (纸本)9798331314385

Adversarial attacks against graph neural networks (GNNs) through perturbations of the graph structure are increasingly common in social network tasks like rumor detection. Social media platforms capture diverse attack sequence samples through both machine and manual screening processes. Investigating effective ways to leverage these adversarial samples to enhance robustness is imperative. We improve the maximum entropy inverse reinforcement learning (IRL) method with the mixture-of-experts approach to address multi-source graph adversarial attacks. This method reconstructs the attack policy, integrating various attack models and providing feature-level explanations, subsequently generating additional adversarial samples to fortify the robustness of detection models. We develop precise sample guidance and a bidirectional update mechanism to reduce the deviation caused by imprecise feature representation and negative sampling within the large action space of social graphs, while also accelerating policy learning. We take rumor detector as an example targeted GNN model on real-world rumor datasets. By utilizing a small subset of samples generated by various graph adversarial attack methods, we reconstruct the attack policy, closely approximating the performance of the original attack method. We validate that samples generated by the learned policy enhance model robustness through adversarial training and data augmentation.

关键词：

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：