检索结果-内蒙古大学图书馆

A nearly optimal distributed algorithm for computing the weighted girth

science China(Information sciences) 2021年第11期64卷 80-94页

作者： Qiang-Sheng HUA Lixiang QIAN Dongxiao YU Xuanhua SHI Hai JIN National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and TechnologyHuazhong University of Science and Technology School of Computer Science and Technology Shandong University

computing the weighted girth, which is the sum of weights of edges in the minimum weight cycle,is an important problem in network analysis. The problem for distributively computing girth in unweighted graphs has garnered lots of attention, but there are few studies in weighted graphs. In this paper, we propose a distributed randomized algorithm for computing the weighted girth in weighted graphs with integral edge weights in the range [1, nc], where n is the number of vertices and c is a constant. The algorithm is devised under the standard synchronous CON GE S T model, which limits each vertex can only transfer O（log n） bits information along each incident edge in a round. The upper bound of the algorithm is O（n log2n） rounds. We also prove the lower bound for computing the weighted girth is ?（D + n/log n） where D is the hop diameter of the weighted graph. This means our distributed algorithm is optimal within a factor of O（log3n）.

关键词： distributed algorithms weighted girth \({\cal C}{\cal O}{\cal N}{\cal G}{\cal E}{\cal S}{\cal T}\) model communication complexity round complexity

来源：评论

学校读者我要写书评

暂无评论

Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency

Detecting Backdoors During the Inference Stage Based on Corr...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Xiaogeng Liu Minghui Li Haoyu Wang Shengshan Hu Dengpan Ye Hai Jin Libing Wu Chaowei Xiao School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Software Engineering Huazhong University of Science and Technology School of Cyber Science and Engineering Wuhan University School of Computer Science and Technology Huazhong University of Science and Technology Cluster and Grid Computing Lab Arizona State University

Deep neural networks are proven to be vulnerable to backdoor attacks. Detecting the trigger samples during the inference stage, i.e., the test-time trigger sample detection, can prevent the backdoor from being triggered. However, existing detection methods often require the defenders to have high accessibility to victim models, extra clean data, or knowledge about the appearance of backdoor triggers, limiting their practicality. In this paper, we propose the test-time corruption robustness consistency evaluation (TeCo) 1 1 https://***/CGCL-codes/TeCo, a novel test-time trigger sample detection method that only needs the hard-label outputs of the victim models without any extra information. Our journey begins with the intriguing observation that the backdoor-infected models have similar performance across different image corruptions for the clean images, but perform discrepantly for the trigger samples. Based on this phenomenon, we design TeCo to evaluate test-time robustness consistency by calculating the deviation of severity that leads to predictions' transition across different corruptions. Extensive experiments demonstrate that compared with state-of-the-art defenses, which even require either certain information about the trigger types or accessibility of clean data, TeCo outperforms them on different backdoor attacks, datasets, and model architectures, enjoying a higher AUROC by 10% and 5 times of stability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multimodal Knowledge Graph Vision-Language Models for Precision Retrieval and Inference in Embedded Systems

Multimodal Knowledge Graph Vision-Language Models for Precis...

引用

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Li, Mingyi Li, Jiayin Liu, Hui Han, Lijin Liao, Dengting Zhang, Zekun Gao, Zong Liu, Baoshuai Jin, Zhongfeng School of Mechanical Engineering Beijing Institute of Technology Beijing100081 China School of Computing and Data Science Xiamen University Malaysia Selangor 43900 Malaysia Shanghai Zhangjiang Institute of Mathematicas Zhangjiang Institute of Shanghai Shanghai201203 China China North Vehicle Research Institute General Technology Department 100072 China Coordination Center of China GNational Computer Network Emergency Response Technical Team 100083 China

ISBN: (纸本)9781665481090

In light of the challenges associated with enhancing multimodal knowledge graph retrieval and improving embodied intelligence in dynamic environments, we propose the Multimodal Knowledge Graph Vision-Language System (MKGVL). This system is designed to enhance the reasoning and feedback capabilities of embodied intelligent systems by continuously updating the knowledge graph through real-time feedback from the Vision-Language Model (VLM). By integrating visual encoders, language models, and knowledge graph networks, MKGVL constructs a unified multimodal representation that enables adaptive decision-making and responsiveness to environmental changes. Experimental results show that MKGVL outperforms existing models in fine-grained retrieval tasks, achieving an 11.5% improvement in Rank1 accuracy and a mean Average Precision (mAP) of 97.49%. Further evaluations conducted on datasets such as ARKitScenes, MultiScan, and 3RScan highlight the model's robustness and adaptability. Additionally, MKGVL's deployment on embedded platforms like Jetson Orin demonstrates its efficiency in real-time multimodal tasks, particularly in resource-constrained environments. These findings underscore MKGVL's ability to deliver accurate and efficient multimodal processing, making it a strong solution for adaptive knowledge-based systems in complex settings. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

One for More: Structured Multi-Modal Hashing for Multiple Multimedia Retrieval Tasks

SSRN

引用

SSRN 2023年

作者： Zheng, Chaoqun Li, Fengling Zhu, Lei Zhang, Zheng Lu, Wenpeng School of Computer Science and Technology Qilu University of Technology Shandong Academy of Sciences China School of Information Science and Engineering Shandong Normal University China Bio-Computing Research Center Harbin Institute of Technology China

Hashing has been widely studied in support of efficient multimedia retrieval due to its high computation and storage efficiency. However, existing multimedia hashing models are designed only for specific multimedia retrieval tasks, e.g., cross-modal retrieval and composite multi-modal retrieval. To simultaneously support multiple multimedia retrieval tasks, multiple different hashing models should be equipped in a multimedia retrieval system. This paper proposes a Structured Multi-Modal Hashing (SMMH) method, which can learn only a hash model for multiple multimedia retrieval tasks. Specifically, we generate structured hash codes by independently projecting the modality data into the Hamming space, where each part of hash codes preserves the specific characteristic of the specific modality data, and they are collaborated to represent the whole multi-modal data. To bridge the heterogeneous gap between multiple modalities, a fusion multi-modal space is constructed based on structured hash codes with label and pair-wise semantic supervision. Besides, we learn hash functions for composite multi-modal retrieval by projecting heterogeneous modalities into the collaborative multi-modal features. Finally, we develop a discrete hash optimization strategy to efficiently solve binary hash codes. Extensive experiments show that our model outperforms the strong baseline methods on multiple multimedia retrieval tasks. Source codes are available at https://***/ChaoqunZheng/SMMH. © 2023, The Authors. All rights reserved.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

“User AR” — Leveraging AI Based Augmented Reality for User Manuals

“User AR” — Leveraging AI Based Augmented Reality for Use...

引用

International Conference on computing and Networking technology (ICCNT)

作者： Thirumurugan Shanmugam Chirag Chandrashekar Vipin Bhati Maheswari Subburaj Arun Kumar Sivaraman Ajmery Sultana College of Computing and Information Sciences University of Technology and Applied Sciences Suhar Oman School of Computer Science and Engineering Vellore Institute of Technology Chennai India Digital Engineering Solution Center Photon Interactive Inc Toronto Ontario Canada School of Computer Science and Technology Algoma University Brampton Ontario Canada

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

The objective of this research is to propose an AI based novel augmented reality (AR) software to assist users in operating a wide range of technical and non-technical devices. The project’s aim is to make this AR application, which provides detailed explanations of all the device’s functions, more widely used than traditional user manuals. Augmented reality, which overlays digital information onto the real world, can be employed to develop an AR-based user manual for products or devices. Mobile applications that use a camera to recognize a product or device and display dynamic graphics, such as 3 D models, animations, or text, are one example of AR user manuals. These augmented reality user manuals enable consumers to quickly and easily learn how to operate, assemble, repair, or troubleshoot their purchased products. Experiments show that the proposed algorithm was able to recognize the object accurately with a percentage of 95.2%.

关键词： Three-dimensional displays Biological system modeling Manuals Transforms Animation Software User experience Artificial intelligence Usability Augmented reality

来源：评论

学校读者我要写书评

暂无评论

PA&DA: Jointly Sampling PAth and DAta for Consistent NAS

arXiv

引用

arXiv 2023年

作者： Lu, Shun Hu, Yu Yang, Longxing Sun, Zihao Mei, Jilin Tan, Jianchao Song, Chengru Research Center for Intelligent Computing Systems Institute of Computing Technology Chinese Academy of Sciences China School of Computer Science and Technology University of Chinese Academy of Sciences China Kuaishou Technology China

Based on the weight-sharing mechanism, one-shot NAS methods train a supernet and then inherit the pre-trained weights to evaluate sub-models, largely reducing the search cost. However, several works have pointed out that the shared weights suffer from different gradient descent directions during training. And we further find that large gradient variance occurs during supernet training, which degrades the supernet ranking consistency. To mitigate this issue, we propose to explicitly minimize the gradient variance of the supernet training by jointly optimizing the sampling distributions of PAth and DAta (PA&DA). We theoretically derive the relationship between the gradient variance and the sampling distributions, and reveal that the optimal sampling probability is proportional to the normalized gradient norm of path and training data. Hence, we use the normalized gradient norm as the importance indicator for path and training data, and adopt an importance sampling strategy for the supernet training. Our method only requires negligible computation cost for optimizing the sampling distributions of path and data, but achieves lower gradient variance during supernet training and better generalization performance for the supernet, resulting in a more consistent NAS. We conduct comprehensive comparisons with other improved approaches in various search spaces. Results show that our method surpasses others with more reliable ranking performance and higher accuracy of searched architectures, showing the effectiveness of our method. Code is available at https://***/ShunLu91/PA-DA. Copyright © 2023, The Authors. All rights reserved.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

Continuous Verification of Catastrophic Recalling in Machine Unlearning via Adversarial Testing

Continuous Verification of Catastrophic Recalling in Machine...

引用

IEEE International Conference on Data science in Cyberspace (DSC)

作者： Y. Neil Qu Zonghao Ji Lei Cui Chong Zhang Lei Liu Zhiyi Tian Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China School of IT Deakin University VIC Australia Guangzhou Institute of Technology Xidian University Guangzhou China School of Computer Science University of Technology Sydney NSW Australia

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

Throughout the process of machine unlearning, in order to fulfill the requirements of machine unlearning and to comply with the rules of the right to be forgotten, it is natural to verify whether the unlearning model actually removes data points. Therefore, machine unlearning verification plays a crucial role. However, existing validation methods only perform one validation, and it is still challenging to determine whether subsequent updates of the model still maintain the unlearning effect. To address this challenge, we propose a novel continuous verification of catastrophic recalling in machine unlearning framework that aims to continuously evaluate whether a machine learning model effectively forgets specified data after an update. In this work, we first introduce adversarial testing as a crucial part of the overall framework. Verification then continues as the unlearned model is updated (adding or continuing to forget data points). We also analyzed the possibility that learning new data after unlearning may diminish the effect. Overall, our continuous unlearning verification framework provides a proactive approach to protecting individual privacy in the machine learning domain, thus facilitating the generation of more robust unlearning algorithms.

关键词： Privacy Machine learning algorithms Cyberspace Machine learning Data science Data models Testing

来源：评论

学校读者我要写书评

暂无评论

How Proficient Are Large Language Models in Formal Languages? An In-Depth Insight for Knowledge Base Question Answering

arXiv

引用

arXiv 2024年

作者： Liu, Jinxin Cao, Shulin Shi, Jiaxin Zhang, Tingjian Nie, Lunyiu Hu, Linmei Hou, Lei Li, Juanzi Department of Computer Science and Technology BNRist THU - Siemens Ltd. China Joint Research Center for Industrial Intelligence and IoT Tsinghua University Beijing China Huawei Cloud Computing Technologies Co. Ltd School of Computer Science and Technology Beijing Institute of Technology China

Knowledge Base Question Answering (KBQA) aims to answer natural language questions based on facts in knowledge bases. A typical approach to KBQA is semantic parsing, which translates a question into an executable logical form in a formal language. Recent works leverage the capabilities of large language models (LLMs) for logical form generation to improve performance. However, although it is validated that LLMs are capable of solving some KBQA problems, there has been little discussion on the differences in LLMs’ proficiency in formal languages used in semantic parsing. In this work, we propose to evaluate the understanding and generation ability of LLMs to deal with differently structured logical forms by examining the inter-conversion of natural and formal language through in-context learning of LLMs. Extensive experiments with models of different sizes show that state-of-the-art LLMs can understand formal languages as well as humans, but generating correct logical forms given a few examples remains a challenge. Most importantly, our results also indicate that LLMs exhibit considerable sensitivity. In general, the formal language with a lower formalization level, i.e., the more similar it is to natural language, is more friendly to LLMs. Code and data can be found at https://***/Matthewlliu/structure_probe. Copyright © 2024, The Authors. All rights reserved.

关键词： Formal languages

来源：评论

学校读者我要写书评

暂无评论

Simulation-Free Hierarchical Latent Policy Planning for Proactive Dialogues

arXiv

引用

arXiv 2024年

作者： He, Tao Liao, Lizi Cao, Yixin Liu, Yuanxing Sun, Yiheng Chen, Zerui Liu, Ming Qin, Bing Research Center for Social Computing and Information Retrieval Harbin Institute of Technology Harbin China Singapore Management University Singapore School of Computer Science Fudan University China

Recent advancements in proactive dialogues have garnered significant attention, particularly for more complex objectives (e.g. emotion support and persuasion). Unlike traditional task-oriented dialogues, proactive dialogues demand advanced policy planning and adaptability, requiring rich scenarios and comprehensive policy repositories to develop such systems. However, existing approaches tend to rely on Large Language Models (LLMs) for user simulation and online learning, leading to biases that diverge from realistic scenarios and result in suboptimal efficiency. Moreover, these methods depend on manually defined, context-independent, coarse-grained policies, which not only incur high expert costs but also raise concerns regarding their completeness. In our work, we highlight the potential for automatically discovering policies directly from raw, real-world dialogue records. To this end, we introduce a novel dialogue policy planning framework, LDPP. It fully automates the process from mining policies in dialogue records to learning policy planning. Specifically, we employ a variant of the Variational Autoencoder to discover fine-grained policies represented as latent vectors. After automatically annotating the data with these latent policy labels, we propose an Offline Hierarchical Reinforcement Learning (RL) algorithm in the latent space to develop effective policy planning capabilities. Our experiments demonstrate that LDPP outperforms existing methods on two proactive scenarios, even surpassing ChatGPT with only a 1.8-billion-parameter LLM. Our codes are available at https://***/cs-holder/***. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Gene ontology and conjunctional false discovery rate statistical framework revealed shared genetic mechanisms underlying glaucoma and myopia

Gene ontology and conjunctional false discovery rate statist...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Shizheng Qiu Xuehui Zhang Yue Liu Zhishuai Zhang Yang Hu Yadong Wang Center for Bioinformatics Faculty of Computing Harbin Institute of Technology Harbin China Beidahuang Industry Group General Hospital Harbin China School of Computer Science and Technology Harbin Institute of Technology Harbin China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Observational studies have demonstrated that refractive error (RE) is associated with an increased risk of primary open-angle glaucoma (POAG). However, the underlying mechanism through which RE influences the development of POAG remains unknown. In this study, we analyzed genome-wide association study (GWAS) data for RE (95,505 participants) and POAG (15,229 cases and 177,473 controls) to characterize polygenic architecture and identify genetic loci shared of these conditions. We integrated the conjunctional false discovery rate (FDR) statistical framework with Gene ontology to investigate the potential biological mechanisms underlying shared genetic loci. Our study revealed a substantial and previously underexplored shared genetic basis between these disorders. Genetic correlation analysis not only confirms overall genetic correlation between RE and POAG (r for genetic = -0.15, 95%CI: -0.21 to -0.09, P = 7.70E07) but also uncovers localized genetic associations, pointing to 12 genome regions of interest. MR analysis established a bidirectional causal relationship between RE and POAG. We identified a robust polygenic overlap between RE and POAG beyond what conventional genetic correlation analysis can reveal. Moreover, we found substantial polygenic overlap and identified 16 shared loci of RE and POAG at conjFDR < 0.01, of which four were novel. Functional annotation offered insights into potential biological mechanisms through which these genetic loci exert their influence, particularly within retinal tissues. Together, this study significantly advances our understanding of the genetic underpinnings that link RE and POAG, elucidating the complex genetic landscape that contributes to their co-occurrence.

关键词： Glaucoma Correlation Annotations Biological tissues Genomics Ontologies Genetics Retina Bioinformatics

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：