检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Xu, Minrui Du, Hongyang Niyato, Dusit Kang, Jiawen Xiong, Zehui Mao, Shiwen Han, Zhu Jamalipour, Abbas Kim, Dong In Shen, Xuemin Leung, Victor C.M. Poor, H. Vincent The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore The School of Automation Guangdong University of Technology Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education Guangzhou510006 China Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore487372 Singapore The Department of Electrical and Computer Engineering Auburn University AuburnAL36849-5201 United States The Department of Electrical and Computer Engineering University of Houston HoustonTX77004 United States The Department of Computer Science and Engineering Kyung Hee University Seoul446-701 Korea Republic of The School of Electrical and Information Engineering University of Sydney SydneyNSW2006 Australia The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of The Department of Electrical and Computer Engineering University of Waterloo WaterlooONN2L 3G1 Canada The College of Computer Science and Software Engineering Shenzhen University Shenzhen518061 China The Department of Electrical and Computer Engineering The University of British Columbia VancouverBCV6T 1Z4 Canada The Department of Electrical and Computer Engineering Princeton University PrincetonNJ08544 United States

Artificial Intelligence-Generated Content (AIGC) is an automated method for generating, manipulating, and modifying valuable and diverse data using AI algorithms creatively. This survey paper focuses on the deployment of AIGC applications, e.g., ChatGPT and Dall-E, at mobile edge networks, namely mobile AIGC networks, that provide personalized and customized AIGC services in real time while maintaining user privacy. We begin by introducing the background and fundamentals of generative models and the lifecycle of AIGC services at mobile AIGC networks, which includes data collection, training, fine-tuning, inference, and product management. We then discuss the collaborative cloud-edge-mobile infrastructure and technologies required to support AIGC services and enable users to access AIGC at mobile edge networks. Furthermore, we explore AIGC-driven creative applications and use cases for mobile AIGC networks. Additionally, we discuss the implementation, security, and privacy challenges of deploying mobile AIGC networks. Finally, we highlight some future research directions and open issues for the full realization of mobile AIGC networks. © 2023, CC BY.

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

Towards Task Sampler Learning for Meta-Learning

arXiv

引用

arXiv 2023年

作者： Wang, Jingyao Qiang, Wenwen Su, Xingzhe Zheng, Changwen Sun, Fuchun Xiong, Hui National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Department of Computer Science and Technology Tsinghua University Beijing China Thrust of Artificial Intelligence Hong Kong University of Science and Technology Guangzhou China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong

Meta-learning aims to learn general knowledge with diverse training tasks conducted from limited data, and then transfer it to new tasks. It is commonly believed that increasing task diversity will enhance the generalization ability of meta-learning models. However, this paper challenges this view through empirical and theoretical analysis. We obtain three conclusions: (i) there is no universal task sampling strategy that can guarantee the optimal performance of meta-learning models;(ii) over-constraining task diversity may incur the risk of under-fitting or overfitting during training;and (iii) the generalization performance of meta-learning models are affected by task diversity, task entropy, and task difficulty. Based on this insight, we design a novel task sampler, called Adaptive Sampler (ASr). ASr is a plug-and-play module that can be integrated into any meta-learning framework. It dynamically adjusts task weights according to task diversity, task entropy, and task difficulty, thereby obtaining the optimal probability distribution for meta-training tasks. Finally, we conduct experiments on a series of benchmark datasets across various scenarios, and the results demonstrate that ASr has clear advantages. The code is publicly available at https://***/WangJingyao07/AdaptiveSampler. Copyright © 2023, The Authors. All rights reserved.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Correction: Enumerating all multi-constrained s–t paths on temporal graph

引用

Knowledge and information systems 2024年第5期66卷 3157-3157页

作者： Jin, Yue Chen, Zijun Liu, Wenyuan School of Information Science and Engineering Yanshan University Qinhuangdao China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao China

来源：评论

学校读者我要写书评

暂无评论

Depression Scale Dictionary Decomposition Framework for Multimodal Automatic Depression Level Prediction

引用

IEEE Transactions on Circuits and systems for Video Technology 2025年第6期35卷 6195-6210页

作者： Niu, Mingyue Wang, Xu Gong, Jibing Liu, Bin Tao, Jianhua Schuller, Bjorn W. Yanshan University School of Information Science and Engineering Hebei province Qinhuangdao066004 China Hebei Key Laboratory of Computer Virtual Technology and System Integration China Technology Co. Ltd Bejing100022 China Bejing100190 China Tsinghua University Department of Automation Bejing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China University of Augsburg ZD.B. Chair of Embedded Intelligence for Health Care and Wellbeing Augsburg Germany Glam - Group on Language Audio and Music United Kingdom

Currently, many researchers aim to achieve automatic depression level prediction via speech and video behavior analysis. However, previous works have struggled to decompose audio and video sequences into the information related to and unrelated to depression scores, hindering the model's perception of depression cues. Besides, previous works implement multimodal fusion using attention mechanisms or linear layers, but failed to simultaneously consider the Euclidean relationship among tokens and the non-Euclidean relationship among channels, which bring limitations in capturing depression cues. In response to the above issues, we propose a depression scale dictionary decomposition framework, which mainly includes a Bidirectional Dictionary Decomposition (BDD) module and a Bidirectional Multimodal Fusion (BMF) module. The BDD module can use the dictionaries generated based on the depression scale to semantically decompose audio and video sequences into the information related to and unrelated to depression scores along token and channel dimensions for promoting depression cue perception. Moreover, considering the respective characteristics of tokens and channels, the BMF module uses linear layers and graph convolution to achieve cross-modal mixing, which is used to aggregate audio and video sequences for predicting depression levels. The validation on AVEC 2013, AVEC 2014 and DAIC-WOZ datasets demonstrates our method's superiority. © 1991-2012 IEEE.

关键词： Boolean functions

来源：评论

学校读者我要写书评

暂无评论

SRoUDA: Meta Self-training for Robust Unsupervised Domain Adaptation

arXiv

引用

arXiv 2022年

作者： Zhu, Wanqing Yin, Jia-Li Chen, Bo-Hao Liu, Ximeng Fujian Province Key Laboratory of Information Security of Network System Fuzhou350108 China College of Computer Science and Big Data Fuzhou University Fuzhou350108 China Department of Computer Science and Engineering Yuan Ze University Taiwan

As acquiring manual labels on data could be costly, unsupervised domain adaptation (UDA), which transfers knowledge learned from a rich-label dataset to the unlabeled target dataset, is gaining increasing popularity. While extensive studies have been devoted to improving the model accuracy on target domain, an important issue of model robustness is neglected. To make things worse, conventional adversarial training (AT) methods for improving model robustness are inapplicable under UDA scenario since they train models on adversarial examples that are generated by supervised loss function. In this paper, we present a new meta self-training pipeline, named SRoUDA, for improving adversarial robustness of UDA models. Based on self-training paradigm, SRoUDA starts with pre-training a source model by applying UDA baseline on source labeled data and taraget unlabeled data with a developed random masked augmentation (RMA), and then alternates between adversarial target model training on pseudo-labeled target data and fine-tuning source model by a meta step. While self-training allows the direct incorporation of AT in UDA, the meta step in SRoUDA further helps in mitigating error propagation from noisy pseudo labels. Extensive experiments on various benchmark datasets demonstrate the state-of-the-art performance of SRoUDA where it achieves significant model robustness improvement without harming clean accuracy. Code is available at https://***/VisionFlow/SRoUDA main. Copyright © 2022, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

QUSL: Quantum Unsupervised Image Similarity Learning with Enhanced Performance

arXiv

引用

arXiv 2024年

作者： Yu, Lian-Hui Li, Xiao-Yu Chen, Geng Zhu, Qin-Sheng Li, Hui Yang, Guo-Wu School of Physics University of Electronic Science and Technology of China Si Chuan Chengdu610054 China School of Information and Software Engineering University of Electronic Science and Technology of China Si Chuan Chengdu610054 China School of Computer Science and Engineering University of Electronic Science and Technology of China Si Chuan Chengdu610054 China JILA Department of Physics University of Colorado BoulderCO80309-0440 United States Advanced Cryptography and System Security Key Laboratory of Sichuan Province Si Chuan Chengdu610103 China

Leveraging quantum properties to enhance complex learning tasks has been proven feasible, with excellent recent achievements in the field of unsupervised learning. However, current quantum schemes neglect adaptive adjustments for unsupervised task scenarios. This work proposes a novel quantum unsupervised similarity learning method — QUSL. Firstly, QUSL uses similarity triplets for unsupervised learning, generating positive samples by perturbing anchor images, achieving a learning process independent of classical algorithms. Subsequently, combining the feature interweaving of triplets, QUSL employs metaheuristic algorithms to systematically explore high- performance mapping processes, obtaining quantum circuit architectures more suitable for unsupervised image similarity tasks. Ultimately, QUSL realizes feature learning with lower quantum resource costs. Comprehensive numerical simulations and experiments on quantum computers demonstrate that QUSL outperforms state-of-the-art quantum methods. QUSL achieves over 50% reduction in critical quantum resource utilization. QUSL improves similarity detection correlation by up to 19.5% across multiple datasets, exhibiting robustness in NISQ environments. While using fewer quantum resources, QUSL shows potential for large-scale unsupervised tasks. © 2024, CC BY-NC-SA.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

QUEST-A: Untrained Filtering with Trained Focusing led to Enhanced Quantum Architectures

arXiv

引用

arXiv 2024年

Quantum architecture search (QAS) represents a fundamental challenge in quantum machine learning, with SOTA methods primarily categorized into training-free and gradient-guided approaches. However, treating QAS solely as either a discrete pruning process or a continuous optimization problem fails to balance accuracy and efficiency. This work decomposes QAS into two alternately solved subproblems: optimal circuit structure retrieval and parameter optimization. Based on this insight, we propose Quantum Untrained-Explored Synergistic Trained Architecture (QUEST-A), which implements rapid architecture pruning through inherent circuit properties and develops focused optimization with parameter reuse strategies. QUEST-A unifies discrete structure search and continuous parameter optimization within an evolutionary framework that integrates rapid pruning and fine-grained optimization. Experiments demonstrate QUEST-A’s superiority over existing methods: enhancing model expressivity in signal representation, maintaining high performance across varying complexities in image classification, and achieving order-of-magnitude precision improvements in variational quantum eigensolver tasks. These results validate QUEST-A’s effectiveness and provide transferable methodologies for QAS. © 2024, CC BY-NC-SA.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Region-based Flash Caching with Joint Latency and Lifetime Optimization in Hybrid SMR Storage systems

Region-based Flash Caching with Joint Latency and Lifetime O...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Zhengang Chen Guohui Wang Zhiping Shi Yong Guan Tianyu Wang College of Information Engineering Capital Normal University Beijing China Beijing Key Laboratory of Electronic System Reliability Technology Capital Normal University Beijing China International Science and Technology Cooperation Base of Electronic System Reliability and Mathematical Interdisciplinary Capital Normal University Beijing China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong China

The frequent Read-Modify-Write operations (RMWs) in Shingled Magnetic Recording (SMR) disks severely degrade the random write performance of the system. Although the adoption of persistent cache (PC) and built-in NAND flash cache alleviates some of the RMWs, when the cache is full, the triggered write-back operations still prolong I/O response time and the erasure of NAND flash also sacrifices its lifetime. In this paper, we propose a Region-based Co-optimized strategy named Multi-Regional Collaborative Management (MCM) to optimize the average response time by separately managing sequential/random and hot/cold data and extend the NAND flash lifetime by a region-aware wear-leveling strategy. The experimental results show that our MCM reduces 71 % of the average response time and 96% of RMWs on average compared with the Skylight (baseline). For the comparison with the state-of-art flash-based cache (FC) approach, we can still save the average response time and flash erase operations by 17.2 % and 33.32 %, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Topic-aware evidence reasoning and stance-aware aggregation for fact verification

arXiv

引用

arXiv 2021年

作者： Si, Jiasheng Zhou, Deyu Li, Tongzhe Shi, Xingyu He, Yulan School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China Department of Computer Science University of Warwick United Kingdom

Fact verification is a challenging task that requires simultaneously reasoning and aggregating over multiple retrieved pieces of evidence to evaluate the truthfulness of a claim. Existing approaches typically (i) explore the semantic interaction between the claim and evidence at different granularity levels but fail to capture their topical consistency during the reasoning process, which we believe is crucial for verification;(ii) aggregate multiple pieces of evidence equally without considering their implicit stances to the claim, thereby introducing spurious information. To alleviate the above issues, we propose a novel topic-aware evidence reasoning and stance-aware aggregation model for more accurate fact verification, with the following four key properties: 1) checking topical consistency between the claim and evidence;2) maintaining topical coherence among multiple pieces of evidence;3) ensuring semantic similarity between the global topic information and the semantic representation of evidence;4) aggregating evidence based on their implicit stances to the claim. Extensive experiments conducted on the two benchmark datasets demonstrate the superiority of the proposed model over several state-of-the-art approaches for fact verification. The source code can be obtained from https://***/jasenchn/TARSA. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation in UAV-NOMA Communication systems Based on Proportional Fairness

引用

Journal of Communications and information Networks 2020年第2期5卷 111-120页

作者： Hui Zhang Baoji Wang Chen Chen Xiang Cheng Hang Li State Key Laboratory of Advanced Optical Communication Systems and Networks Department of ElectronicsSchool of Electronics Engineering and Computer SciencePeking UniversityBeijing 100871China Shanghai Institute of Microsystem and Information Tech-nology Chinese Academy of SciencesShanghai 200050China Data-Driven Information System Laboratory Shenzhen Re-search Institute of Big DataShenzhen 518172China

This paper investigates the power allocation problem in non-orthogonal multiple access(NOMA)integrated unmanned aerial vehicle(UAV)communication *** particular,we propose a novel resource allocation scheme to increase the transmission rate of the users that have relatively worse channel state information,while reducing the sum rate *** solve this problem efficiently,we decouple the optimization problem into three ***,we solve the problem of user pairing and subchannel ***,the optimum power proportional factor is derived to allocate transmit power among different users on the same *** last,different subchannels are allocated with appropriate power to improve the performance of the *** results show that the proposed scheme can enjoy a better performance than the benchmark methods since it can achieve a proper trade-off between the system sum rate and the proportional fairness.

关键词： UAV communications NOMA power allo-cation proportional fairness

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：