检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Du, Jing Ye, Zesheng Guo, Bin Yu, Zhiwen Wu, Jia Yang, Jian Sheng, Michael Yao, Lina School of Computing Macquarie University SydneyNSW2109 Australia School of Computing and Information Systems University of Melbourne MelbourneVIC3052 Australia School of Computer Science Northwestern Polytechnical University Shaanxi Xi’an China Data 61 CSIRO SydneyNSW2122 Australia School of Computer Science and Engineering University of New South Wales SydneyNSW2015 Australia

Recent cross-domain recommendation (CDR) studies assume that disentangled domain-shared and domain-specific user representations can mitigate domain gaps and facilitate effective knowledge transfer. However, achieving perfect disentanglement is challenging in practice, because user behaviors in CDR are highly complex, and the true underlying user preferences cannot be fully captured through observed user-item interactions alone. Given this impracticability, we instead propose to model joint identifiability that establishes unique correspondence of user representations across domains, ensuring consistent preference modeling even when user behaviors exhibit shifts in different domains. To achieve this, we introduce a hierarchical user preference modeling framework that organizes user representations by the neural network encoder’s depth, allowing separate treatment of shallow and deeper subspaces. In the shallow subspace, our framework models the interest centroids for each user within each domain, probabilistically determining the users’ interest belongings and selectively aligning these centroids across domains to ensure fine-grained consistency in domain-irrelevant features. For deeper subspace representations, we enforce joint identifiability by decomposing it into a shared cross-domain stable component and domain-variant components, linked by a bijective transformation for unique correspondence. Empirical studies on real-world CDR tasks with varying domain correlations demonstrate that our method consistently surpasses state-of-the-art, even with weakly correlated tasks, highlighting the importance of joint identifiability in achieving robust CDR. © 2024, CC BY-NC-SA.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

Copula Guided Parallel Gibbs Sampling for Nonparametric and Coherent Topic Discovery (Extended Abstract) 39

Copula Guided Parallel Gibbs Sampling for Nonparametric and ...

引用

39th IEEE International Conference on data Engineering, ICDE 2023

作者： Lin, Lihui Rao, Yanghui Xie, Haoran Lau, Raymond Y. K. Yin, Jian Wang, Fu Lee Li, Qing Sun Yat-sen University School of Computer Science and Engineering Guangzhou China Lingnan University Department of Computing and Decision Sciences New Territories Hong Kong City University of Hong Kong Department of Information Systems Kowloon Hong Kong Sun Yat-sen University Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Hong Kong Metropolitan University School of Science and Technology Kowloon Hong Kong The Hong Kong Polytechnic University Department of Computing Kowloon Hong Kong

ISBN: (纸本)9798350322279

In terms of the generative process, the Gamma-Gamma-Poisson Process (G2PP) is equivalent to the nonparametric topic model of Hierarchical Dirichlet Process (HDP). Considering the high computational cost of estimating parameters in HDP, a parallel G2PP was developed to generate topics efficiently via multi-threading. Unfortunately, the above model needs to predefine the number of topics. To address this issue, we first propose a Topic Self-Adaptive Model (TSAM) for nonparametric and parallel topic discovery. In TSAM, a monitor-executor mechanism is developed to manage the global topic information using a hierarchical structure of threads. Based on the apparatus of copulas, we further extend our TSAM to TSAMcop for coherent topic modeling by exploiting a copula guided parallel Gibbs sampling algorithm. Extensive experiments validate the effectiveness of both TSAM and TSAMcop. © 2023 IEEE.

关键词： information management

来源：评论

学校读者我要写书评

暂无评论

Covert Communication in RSMA-Assisted Ambient Backscatter Communication Systems

引用

IEEE Transactions on Wireless Communications 2025年

作者： Zhang, Zhuo Yang, Liang Lei, Hongjiang Li, Xingwang Niyato, Dusit Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Hunan University College of Computer Science and Electronic Engineering China Jishou University School of Communication and Electronic Engineering China Chongqing University of Posts and Telecommunications School of Communications and Information Engineering The Chongqing Key Laboratory of Mobile Communications Technology Chongqing400065 China Henan Polytechnic University School of Physics and Electronic Information Engineering Jiaozuo454003 China Nanyang Technological University College of Computing and Data Science Singapore639798 Singapore

In this paper, we investigate covert communication in rate-splitting multiple access (RSMA)-assisted ambient backscatter communication (AmBC) systems. Specifically, in the presence of illegitimate users, a base station applies RSMA to the downlink transmission of covert users and common users in the the primary system of ambient backscatter. To evaluate the covertness of the system, we derive closed-form expressions for the detection error probability (DEP), outage probability (OP), and covert rate (CR), where the DEP is applied to evaluate the ability of the warden to detect the presence or absence of communication behaviors between the base station and the covert user. Based on these expressions, we also conduct an asymptotic analysis of the outage probability, an upper bound analysis of the covert rate, and an analysis of the impact of the power allocation factor on system performance. Numerical results show that the RSMA scheme has a higher covert rate and a higher minimum DEP value compared to the non-orthogonal multiple access (NOMA) scheme, but it may reduce its outage performance. Additionally, an appropriate use of the power allocation factor can enhance the covertness of the system. Furthermore, we find that the co-channel interference between the primary and secondary systems in the ambient backscatter system can degrade the covert performance of the primary system. © 2002-2012 IEEE.

关键词： Backscattering

来源：评论

学校读者我要写书评

暂无评论

MOAC: Multi-Objective Adaptive Clustering Optimization Algorithm Based on Cluster Adaptation

MOAC: Multi-Objective Adaptive Clustering Optimization Algor...

引用

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Hossam M. J. Mustafa Dheeb Albashish Ahmad Khasawneh Department of Data Science and Artificial Intelligence Faculty of Information Technology University of Petra Amman Jordan Computer Science Department Prince Abdullah bin Ghazi Faculty of Information and Communication Technology Al-Balqa Applied University Salt Jordan School of Computing Skyline University College Sharjah UAE

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

This paper presents a novel Multi-Objective Adaptive Clustering (MOAC) algorithm that addresses current limitations in existing multi-objective optimization methods. While current algorithms often struggle with premature convergence and diversity preservation, the MOAC algorithm proposes a novel clustering-based approach to search space by partitioning. The algorithm combines cluster evolution with an adaptive parameter control mechanism to achieve significant improvements in balancing exploration-exploitation and diversity maintenance. MOAC employs k-means clustering for population partitioning, combined with cluster-based genetic operators, and an efficient diversity preservation scheme. Extensive experiments across different ZDT, MMF, and UF test suites demonstrate that MOAC's performance is superior, which achieves outstanding hypervolume and IGD values in complex multi-modal problems. The algorithm shows strength in handling complex Pareto fronts, and comprehensive statistical analysis through the Friedman rankings test with a 2.21 rank. Moreover. The results reveal that MOAC is a robust approach for complex multi-objective optimization problems, particularly maintaining solution diversity and achieving consistent convergence across different problems.

关键词： Ranking (statistics) Statistical analysis Metaheuristics Clustering algorithms Optimization methods Evolutionary computation Partitioning algorithms Maintenance Convergence Genetic operators

来源：评论

学校读者我要写书评

暂无评论

Label Distribution Learning with Correlation information

SSRN

引用

SSRN 2024年

作者： Wu, Yilin Lin, Yaojin Guo, Wenzhong Ding, Weiping College of Computer and Data Science Fuzhou University Fuzhou350116 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China Key Laboratory of Data Science and Intelligence Application Minnan Normal University Zhangzhou363000 China School of Information Science and Technology Nantong University Nantong226019 China

Label distribution learning quantifies the label space for each instance and has widely applicability in different fields. However, most existing works primarily focus on label correlation, but they still have a limitation in capturing instance correlation. Meanwhile, traditional label distribution learning operates on individual labels sequentially, leading to limitation in applying common features. Therefore, in this paper, we propose a novel approach for label distribution learning with correlation information i.e. instance correlation and label correlation. Specifically, the instance correlation and label correlation are identified by an optimization function and Pearson correlation coefficient, respectively. Besides, we conduct $\ell_{2,1}-$norm regularization to exploit common features. Comprehensive experiments manifest the superiority of our proposed approach against other well-established label distribution learning algorithms. © 2024, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectors

arXiv

引用

arXiv 2024年

作者： Zhou, Ziqi Li, Bowen Song, Yufei Yu, Zhifei Hu, Shengshan Wan, Wei Zhang, Leo Yu Yao, Dezhong Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Computer Science and Technology Huazhong University of Science and Technology China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

With the advancement of deep learning, object detectors (ODs) with various architectures have achieved significant success in complex scenarios like autonomous driving. Previous adversarial attacks against ODs have been focused on designing customized attacks targeting their specific structures (e.g., NMS and RPN), yielding some results but simultaneously constraining their scalability. Moreover, most efforts against ODs stem from image-level attacks originally designed for classification tasks, resulting in redundant computations and disturbances in object-irrelevant areas (e.g., background). Consequently, how to design a model-agnostic efficient attack to comprehensively evaluate the vulnerabilities of ODs remains challenging and unresolved. In this paper, we propose NumbOD, a brand-new spatial-frequency fusion attack against various ODs, aimed at disrupting object detection within images. We directly leverage the features output by the OD without relying on its internal structures to craft adversarial examples. Specifically, we first design a dual-track attack target selection strategy to select high-quality bounding boxes from OD outputs for targeting. Subsequently, we employ directional perturbations to shift and compress predicted boxes and change classification results to deceive ODs. Additionally, we focus on manipulating the high-frequency components of images to confuse ODs' attention on critical objects, thereby enhancing the attack efficiency. Our extensive experiments on nine ODs and two datasets show that NumbOD achieves powerful attack performance and high stealthiness. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Robust Optical Quantum Imaging Framework with Entangled Photons in Oceanic Turbulent Environments

引用

IEEE Transactions on Communications 2025年

作者： Cao, Jingyang Zhou, Mu Zhang, Ruichen Niyato, Dusit Nie, Wei Han, Zhu Chongqing University of Posts and Telecommunications School of Communications and Information Engineering Chongqing China Nanyang Technological University College of Computing and Data Science Nanyang China University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

As an important part of underwater optical technology, underwater imaging plays a crucial role in accurately capturing underwater targets and environmental features. Facing the challenges of complex ocean environments and severe photon attenuation, quantum imaging breaks through the limitations of traditional optical imaging technology by utilizing the characteristics of two-photon entanglement and time-space correlation, thus offering a new perspective on ocean turbulence. To this end, we propose a new underwater entangled-photon quantum imaging system. Specifically, we first construct an entangled photon quantum imaging physical model through ocean long-exposure turbulence and then exploit an entangled light co-incidence imaging reconstruction method to image the target object. Furthermore, in response to the problem that ocean environment has a great impact on photons, we develop a photon capture probability method based on entangled photon pairs to reduce the impact of the ocean turbulence noise on imaging and improve the underwater target imaging resolution. We experimentally demonstrate the effectiveness of our method by showing that even in harsh ocean environments, quantum imaging performs superior resolution capabilities over traditional light source imaging techniques. © 1972-2012 IEEE.

关键词： Quantum entanglement

来源：评论

学校读者我要写书评

暂无评论

Text-guided Reconstruction Network for Sentiment Analysis with Uncertain Missing Modalities

引用

IEEE Transactions on Affective computing 2025年

作者： Shi, Piao Hu, Min Nakagawa, Satoshi Zheng, Xiangming Shi, Xuefeng Ren, Fuji Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine National Smart Eldercare International Science and Technology Cooperation Base School of Computer Science and Information Engineering Anhui Hefei230601 China Bozhou University School of Electronic and Information Engineering Bozhou236800 China University of Tokyo Graduate School of Information Science and Technology Tokyo113-8656 Japan University of Electronic Science and Technology of China College of Computer Science and Engineering Chengdu611731 China University of Electronic Science and Technology of China Shenzhen Institute for Advanced Study Shenzhen518110 China

Multimodal Sentiment Analysis (MSA) is an attractive research that aims to integrate sentiment expressed in textual, visual, and acoustic signals. There are two main problems in the existing methods: 1) the dominant role of the text is underutilization in unaligned multimodal data, and 2) the modality under uncertain missing feature is not sufficiently explored. This paper proposes a Text-guided Reconstruction Network (TgRN) for MSA with uncertain missing modalities in non-aligned sequences. The TgRN network includes three primary modules: Text-guided Extraction Module (TEM), Reconstruction Module (RM) and Text-guided Fusion Module (TFM). First, the TEM consists of the text-guided cross attention units and self-attention units to capture inter-modal features and intra-modal features, respectively. Second, leveraging enhanced attention units and a three-way squeeze-and-excitation block, the RM is designed to learn semantic information from incomplete data and reconstruct missing modality features. Third, the TFM utilizes a progressive modality-mixing adaptation gate to explore the dynamic correlations between nonverbal and verbal modalities, effectively addressing the modality gap issue. Finally, under the supervision of sentiment prediction loss and reconstruction loss, the TgRN effectively processes both uncertain missing-modality conditions and ideal complete modality conditions. Extensive experiments on CMU-MOSI and CH-SIMS demonstrate that our proposed method outperforms state-of-the-art approaches. © 2010-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Wiki-match:A multi-model pipeline for image-caption matching task on Wikipedia dataset

Wiki-match:A multi-model pipeline for image-caption matching...

引用

作者： Yibing Chen Siyu Lei Zhouhang Sun School of Computing and Information System Singapore Management University School of Computer Science Sichuan University School of Data Science The Chinese University of Hongkong(Shenzhen)

We propose a multi-model pipeline for image-caption matching tasks on Wikipediabased dataset which leverages object-detection technique and attention mechanism to achieve fine-grained matching between textual representation and image *** from the prior research,we not only evaluate our pipeline effectiveness on common benchmark dataset such as MS-COCO and Flickr30k,but also a new dataset that is derived from Wikipedia which is rich in natural entities and abstract *** findings show:1) our model pipeline improves R@1 by 113.4%,R@3 by 86.1%,and R@5 by 114.4% compared to the original pipeline provided by the Wikipedia-based dataset.2) our model pipeline has close to the state-of-the-art performance in common benchmark dataset including Flickr30k and MS-COCO.3) images that are from Wikipedia creates bigger challenges for models to understand compares to MS-COCO or Flickr30k due to the abstract concepts and broad topics covered by Wikipedia.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ACE-RLHF: Automated Code Evaluation and Socratic Feedback Generation Tool using Large Language Models and Reinforcement Learning with Human Feedback

arXiv

引用

arXiv 2025年

作者： Rahman, Tasnia Kumar, Sathish A.P. Jha, Sumit Ramanathan, Arvind Department of Computer Science Cleveland State University ClevelandOH United States School of Computing and Information Sciences Florida International University MiamiFL United States Data Science and Learning Division Argonne National Laboratory LemontIL United States

Automated Program Repair tools are developed for generating feedback and suggesting a repair method for erroneous code. State of the art (SOTA) code repair methods rely on data-driven approaches and often fail to deliver solution for complicated programming questions. To interpret the natural language of unprecedented programming problems, using Large Language Models (LLMs) for code-feedback generation is crucial. LLMs generate more comprehensible feedback than compiler-generated error messages, and Reinforcement Learning with Human Feedback (RLHF) further enhances quality by integrating human-in-the-loop which helps novice students to lean programming from scratch interactively. We are applying RLHF fine-tuning technique for an expected Socratic response such as a question with hint to solve the programming issue. We are proposing code feedback generation tool by fine-tuning LLM with RLHF, Automated Code Evaluation with RLHF (ACE-RLHF), combining two open-source LLM models with two different SOTA optimization techniques. The quality of feedback is evaluated on two benchmark datasets containing basic and competition-level programming questions where the later is proposed by us. We achieved 2-5% higher accuracy than RL-free SOTA techniques using Llama-3-7B-Proximal-policy optimization in automated evaluation and similar or slightly higher accuracy compared to reward model-free RL with AI Feedback (RLAIF). We achieved almost 40% higher accuracy with GPT-3.5 Best-of-n optimization while performing manual evaluation. © 2025, CC BY.

关键词： Reinforcement learning

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：