检索结果-内蒙古大学图书馆

Q&A driven conversational recommendation integrating multiple interest modeling

Neurocomputing 2025年 647卷

作者： Haiping Zhu Yuqi Sun Shuwei Che Yan Chen School of Computer Science and Technology Xi’an Jiaotong University Xi’an 710049 China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Xi’an 710049 China Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an 710049 China

The conversational recommendation aims to provide users with recommendations in an interaction form of “System Ask-User Respond”. Existing studies rarely consider combining users’ multi-interest at the attribute level for preference modeling, and conduct inefficient conversational recommendation strategy learning, which affects the recommendation performance and conversation performance. To this end, we proposed a Q-A driven conversational recommendation method integrating multiple interest modeling. Specifically, we integrate the user’s positive and negative feedback to model a session dynamic graph, then use the signed graph convolutional network for graph representation learning, and we model multiple interest sequences based on the attention mechanism, then obtain the user interest state representation by fusing of sequence representations to solve the problem of insufficient user preference representation. Besides, we proposed a personalized decision space optimization method to narrow the range of action candidates and train the model with a multi-agent reinforcement learning method integrating hierarchical decision debiasing to solve the problem of poor conversational recommendation strategy learning effect. Experimental results on three public datasets, LastFM, Yelp, and Book, show that compared with existing conversational recommendation methods, our method demonstrates consistent performance improvement across all datasets. In addition, the results of ablation experiments verify the effectiveness of each component in our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advances in resonator-based Kerr frequency combs with high conversion efficiencies

npj Nanophotonics

引用

npj Nanophotonics 2024年第1期1卷 1-21页

作者： Xucheng Zhang Chunxue Wang Zhibo Cheng Congyu Hu Xingchen Ji Yikai Su John Hopcroft Center for Computer Science School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai 200240 China State Key Laboratory of Advanced Optical Communication Systems and Networks Department of Electronic Engineering Shanghai Jiao Tong University Shanghai 200240 China

Recent developments in resonator-based Kerr frequency combs promise excellent applications in a wide range of fields such as biosensing, spectroscopy, optical communications, light detection and ranging (LiDAR), frequency synthesis, astronomical detection, and quantum optics. A key figure of merit (FOM) for Kerr frequency combs is the pump-to-comb conversion efficiency, which is critical for applications requiring sufficient comb power and low power consumption. In this review, we first discuss the limited conversion efficiency of dissipative Kerr soliton in an anomalous dispersion microresonator based on its underlying physical characteristics. And then, we summarize the recent advances in Kerr frequency combs with high conversion efficiencies in both anomalous and normal dispersion regimes. We classify them according to various soliton states, excitation methods as well as novel material platforms. The final section of the paper presents an overview of current progress and glances at potential directions for future research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Zero-Added-Loss Entangled Photon Multiplexing for Ground- and Space-Based Quantum networks

arXiv

引用

arXiv 2022年

作者： Chen, Kevin C. Dhara, Prajit Heuck, Mikkel Lee, Yuan Dai, Wenhan Guha, Saikat Englund, Dirk Research Laboratory of Electronics Massachusetts Institute of Technology CambridgeMA02139 United States Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA02139 United States Wyant College of Optical Sciences The University of Arizona TucsonAZ85721 United States NSF-ERC Center for Quantum Networks The University of Arizona TucsonAZ85721 United States Department of Electrical and Photonics Engineering Technical University of Denmark Kgs. Lyngby2800 Denmark College of Information and Computer Science University of Massachusetts AmherstMA01003 United States Brookhaven National Laboratory UptonNY11973 United States

We propose a scheme for optical entanglement distribution in quantum networks based on a quasi-deterministic entangled photon pair source. By combining heralded photonic Bell pair generation with spectral mode conversion to interface with quantum memories, the scheme eliminates switching losses due to multiplexing in the source. We analyze this 'zero-added-loss multiplexing' (ZALM) Bell pair source for the particularly challenging problem of long-baseline entanglement distribution via satellites and ground-based memories, where it unlocks additional advantages: (i) the substantially higher channel efficiency η of downlinks vs. uplinks with realistic adaptive optics, and (ii) photon loss occurring before interaction with the quantum memory - i.e., Alice and Bob receiving rather than transmitting - improve entanglement generation rate scaling by O(√η). Based on numerical analyses, we estimate our protocol to achieve > 10 ebit/s at memory multiplexing of 102 spin qubits for ground distance > 102 km, with the spin-spin Bell state fidelity exceeding 99%. Our architecture presents a blueprint for realizing global-scale quantum networks in the near-term. © 2022, CC BY.

关键词： Quantum entanglement

来源：评论

学校读者我要写书评

暂无评论

A portable rotational sensor based on the dual-polarization fiber optic gyroscope

A portable rotational sensor based on the dual-polarization ...

引用

Asia Communications and Photonics Conference and Exhibition (ACP)

作者： Yuwen Cao Lanxin Zhu Tong Zhou Chunxia Yang Yanjun Chen Zhengbin Li State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Engineering and Computer Science Peking University Beijing China School of Software and Microelectronics Peking University Beijing China Youfu Technology Co. Ltd Hangzhou China

A portable rotational sensor based on a modified dual-polarization fiber optic gyroscope is demonstrated, in which the excess relative intensity noise is effectively com-pensated achieving an enhanced sensitivity of 7... 详细信息

ISBN: (纸本)9781957171005

关键词： Optical fiber sensors Sensitivity Seismology Prototypes Optical fiber communication Thermal noise Gyroscopes

来源：评论

学校读者我要写书评

暂无评论

Enhancing Security of NOMA networks via Distributed Intelligent Reflecting Surfaces

Enhancing Security of NOMA Networks via Distributed Intellig...

引用

2021 IEEE Global Communications Conference (GLOBECOM)

作者： Zheng Zhang Jian Chen Qingqing Wu Yuanwei Liu Lu Lv Xunqi Su State Key Laboratory of Integrated Services Networks Xidian University Xi'an China State Key Laboratory of Internet of Things for Smart City University of Macau Macau China National Mobile Communications Research Laboratory Southeast University Nanjing China School of Electronic Engineering and Computer Science Queen Mary University of London London U.K

ISBN: (纸本)9781728181059

This paper investigates the security enhancement of an intelligent reflecting surface (IRS) assisted non-orthogonal multiple access (NOMA) network, where a distributed IRS enabled NOMA transmission framework is proposed to serve users securely in the presence of a passive eavesdropper. Considering that the instantaneous channel state information (CSI) of the eavesdropper is challenging to acquire in practice, we utilize the secrecy outage probability (SOP) as the security metric. A problem by jointly optimizing the transmit power at the base station (BS) and reflection phase shifts at IRSs, subject to the successive interference cancellation (SIC) decoding constraints and SOP constraints, is formulated to maximize the minimum secrecy rate among legitimate users. To tackle the non-convex problem, we first derive the exact SOP in closed-form expressions and then propose a novel ring-penalty based successive convex approximation (SCA) algorithm to design power allocation and phase shifts jointly. Numerical results validate the convergence and the secrecy superiority of proposed scheme over the baseline schemes.

关键词： NOMA Silicon carbide Probability Reflection Decoding Reflection coefficient Power system reliability

来源：评论

学校读者我要写书评

暂无评论

Registration-Based Bilateral Fine-Grained Access Control in Vehicular Social networks

引用

IEEE Internet of Things Journal 2025年

作者： Ming, Yang Wang, Hongyu Wang, Chenhao Liu, Hang Feng, Jie Li, Keqin Chang’an University School of Information Engineering Xi’an710064 China Xidian University State Key Laboratory of Integrated Service Networks Xi’an710071 China State University of New York Department of Computer Science New PaltzNY12561 United States

Vehicular Social networks (VSNs), as an innovative mobile communication system, significantly enhance the driving experience and improve urban traffic management efficiency. To address the privacy issues that arise from the use of public channels in VSNs, fine-grained access control should be ensured. Nevertheless, existing schemes still face some practical challenges in the aspects of data source identification, key escrow, and dynamic vehicle management. Therefore, this paper proposes a registration-based bilateral fine-grained access control scheme (RBF-AC) in VSNs. Specifically, RBF-AC allows service providers to select target vehicles and offer tailored services, while allowing vehicles to identify the most suitable service providers based on their needs, and all of which are realized in a fine-grained level. Meanwhile, service providers and vehicles are capable of locally generating their own private and public keys without relying on any fully trusted authority. RBF-AC also keeps high flexibility and enables the vehicles to join, leave and update their attributes in a dynamic manner. Additionally, outsourced verification and decryption are provided to minimize the computation cost for vehicles. We present formal security proofs to validate the security of RFB-AC. The performance evaluation illustrates the practical applicability of RBF-AC in VSNs. © 2014 IEEE.

关键词： Authorization

来源：评论

学校读者我要写书评

暂无评论

Beamforming Design and Association Scheme for Multi-RIS Multi-User mmWave Systems Through Graph Neural networks

arXiv

引用

arXiv 2025年

作者： Liu, Mengbing Huang, Chongwen Alhammadi, Ahmed Di Renzo, Marco Debbah, Mérouane Yuen, Chau School of Electrical and Electronics Engineering Nanyang Technological University 639798 Singapore College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China Zhejiang Provincial Key Laboratory of Multi-Modal Communication Networks and Intelligent Information Processing Hangzhou310027 China Technology Innovation Institute Masdar City Abu Dhabi United Arab Emirates Université Paris-Saclay CNRS CentraleSupélec Laboratoire des Signaux et Systèmes 3 Rue Joliot-Curie Gif-sur-Yvette91192 France King’s College London Centre for Telecommunications Research Department of Engineering LondonWC2R 2LS United Kingdom KU 6G Research Center Department of Computer and Information Engineering Khalifa University Abu Dhabi127788 United Arab Emirates CentraleSupelec University Paris-Saclay Gif-sur-Yvette91192 France

Reconfigurable intelligent surface (RIS) is emerging as a promising technology for next-generation wireless communication networks, offering a variety of merits such as the ability to tailor the communication environment. Moreover, deploying multiple RISs helps mitigate severe signal blocking between the base station (BS) and users, providing a practical and efficient solution to enhance the service coverage. However, fully reaping the potential of a multi-RIS aided communication system requires solving a non-convex optimization problem. This challenge motivates the adoption of learning-based methods for determining the optimal policy. In this paper, we introduce a novel heterogeneous graph neural network (GNN) to effectively leverage the graph topology of a wireless communication environment. Specifically, we design an association scheme that selects a suitable RIS for each user. Then, we maximize the weighted sum rate (WSR) of all the users by iteratively optimizing the RIS association scheme, and beamforming designs until the considered heterogeneous GNN converges. Based on the proposed approach, each user is associated with the best RIS, which is shown to significantly improve the system capacity in multi-RIS multiuser millimeter wave (mmWave) communications. Specifically, simulation results demonstrate that the proposed heterogeneous GNN closely approaches the performance of the high-complexity alternating optimization (AO) algorithm in the considered multi-RIS aided communication system, and it outperforms other benchmark schemes. Moreover, the performance improvement achieved through the RIS association scheme is shown to be of the order of 30%. Copyright © 2025, The Authors. All rights reserved.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

Fast all-optical random number generator

arXiv

引用

arXiv 2022年

作者： Zhao, Jiamin Li, Pu Zhang, Xing Gao, Zhensen Jia, Zhiwei Bogris, Adonis Alan Shore, K. Wang, Yuncai Key Laboratory of Advanced Transducers and Intelligent Control System Ministry of Education Taiyuan University of Technology Taiyuan030024 China School of Information Engineering Guangdong University of Technology Guangzhou510006 China Guangdong Provincial Key Laboratory of Photonics Information Technology Guangzhou510006 China Key Laboratory of Specialty Fiber Optics and Optical Access Networks Shanghai University Shanghai200444 China Changchun Institute of Optics Fine Mechanics and Physics Chinese Academy of Sciences Changchun130033 China Department of Informatics and Computer Engineering University of West Attica Athens12243 Greece School of Electronic Engineering Bangor University WalesLL57 1UT United Kingdom

We propose a simple and all-optical method for fast random number generation based on the laser mode hopping. Through periodically restarting a two-mode laser operating in the bistable state, a random number stream can be generated due to the spontaneous emission noise. To validate the feasibility of this method, we perform a theoretical simulation using the common vertical-cavity surface-emitting laser (VCSEL) with two polarization modes. Numerical results demonstrate that fast 2.5 Gb/s random number streams can be continuously obtained with verified randomness. This scheme provide a fully monolithic solution for random number generator, due to its simple and all-optical structure. Copyright © 2022, The Authors. All rights reserved.

关键词： Random number generation

来源：评论

学校读者我要写书评

暂无评论

Object-oriented Vegetation Classification Method based on UAV and Satellite Image Fusion 8

Object-oriented Vegetation Classification Method based on UA...

引用

8th International Conference on Identification, Information and Knowledge in the Internet of Things, IIKI 2019

作者： Zhao, Fuchao Wu, Xiaoming Wang, Shuai College of Computer Science and Engineering Shandong University of Science and Technology Shandong University of Science and Technology No. 579 qianwangang road Qingdao266590 China Shandong Provincial Key Laboratory of Computer Networks Shandong Academy of Sciences NO.19 keyuan road Jinan250014 China Biological Engineering Technology Innovation Center of Shandong Province No.1999 north outer ring road Heze274009 China

Nowadays, space remote sensing technology has become one of the most important means for people to obtain geographic information and environmental information. Satellite multi-spectral data contains rich spectral information in multiple bands. The method of remote sensing monitoring of ground vegetation classification and identification represented by satellite is widely used. Because the Unmanned Aerial Vehicle (UAV) has obvious advantages such as small size, strong timeliness, flexible operation and low cost, it is widely used as a remote sensing platform for disaster monitoring, environmental detection, vegetation distribution information monitoring, etc. And it quickly becomes an important way to get the vegetation type of the study area. Compared with satellite multi-spectral images, UAV images have high resolution and rich spatial information, but lack spectral information for vegetation identification. So this article is based on satellite images, in order to improve the precision of ground vegetation in the area of classification and recognition, the UAV images and satellite multi-spectral images data pixel level fusion, combined with object-oriented supervised classification method, the integration of data with random forests (RF), support vector machine (SVM) and maximum likelihood estimation (MLE) method for vegetation classification identification precision and validation. Compared with the data before fusion, the statistical results of the confusion matrix output show that the accuracy of vegetation classification recognition under the combination of object-oriented supervised classification method has been significantly improved. © 2020 The Authors. Published by Elsevier B.V.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

WeClick: Weakly-supervised video semantic segmentation with click annotations

arXiv

引用

arXiv 2021年

作者： Liu, Peidong He, Zibin Yan, Xiyu Jiang, Yong Xia, Shu-Tao Zheng, Feng Hu, Maowei Tsinghua Shenzhen International Graduate School Tsinghua University PCL Research Center of Networks and Communications Peng Cheng Laboratory Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen Rejoice Sport Tech. Co. LTD

Compared with tedious per-pixel mask annotating, it is much easier to annotate data by clicks, which costs only several seconds for an image. However, applying clicks to learn video semantic segmentation model has not been explored before. In this work, we propose an effective weakly-supervised video semantic segmentation pipeline with click annotations, called WeClick, for saving laborious annotating effort by segmenting an instance of the semantic class with only a single click. Since detailed semantic information is not captured by clicks, directly training with click labels leads to poor segmentation predictions. To mitigate this problem, we design a novel memory flow knowledge distillation strategy to exploit temporal information (named memory flow) in abundant unlabeled video frames, by distilling the neighboring predictions to the target frame via estimated motion. Moreover, we adopt vanilla knowledge distillation for model compression. In this case, WeClick learns compact video semantic segmentation models with the low-cost click annotations during the training phase yet achieves real-time and accurate models during the inference period. Experimental results on Cityscapes and Camvid show that WeClick outperforms the state-of-the-art methods, increases performance by 10.24% mIoU than baseline, and achieves real-time execution. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantic Segmentation

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：