检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Di, Hao Ye, Haishan Chang, Xiangyu Dai, Guang Tsang, Ivor W. Center for Intelligent Decision-Making and Machine Learning School of Management Xi'an Jiaotong University China SGIT AI Lab State Grid Corporation of China China College of Computing and Data Science NTU Singapore Singapore

In decentralized optimization, m agents form a network and only communicate with their neighbors, which gives advantages in data ownership, privacy, and scalability. At the same time, decentralized stochastic gradient descent (SGD) methods, as popular decentralized algorithms for training large-scale machine learning models, have shown their superiority over centralized counterparts. Distributed stochastic gradient tracking (DSGT) (Pu & Nedić, 2021) has been recognized as the popular and state-of-the-art decentralized SGD method due to its proper theoretical guarantees. However, the theoretical analysis of DSGT (Koloskova et al., 2021) shows that its iteration complexity is (equation presented) where the doubly stochastic matrix W represents the network topology and CW is a parameter that depends on W. Thus, it indicates that the convergence property of DSGT is heavily affected by the topology of the communication network. To overcome the weakness of DSGT, we resort to the snapshot gradient tracking skill and propose two novel algorithms, snap-shot DSGT (SS DSGT) and accelerated snap-shot DSGT (ASS DSGT). We further justify that SS DSGT exhibits a lower iteration complexity compared to DSGT in the general communication network topology. Additionally, ASS DSGT matches DSGT's iteration complexity (equation presented) under the same conditions as DSGT. Numerical experiments validate SS DSGT's superior performance in the general communication network topology and exhibit better practical performance of ASS DSGT on the specified W compared to DSGT. Copyright 2024 by the author(s)

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

Fast Parallel Recovery for Transactional Stream Processing on Multicores 40

Fast Parallel Recovery for Transactional Stream Processing o...

引用

40th IEEE International Conference on data Engineering, ICDE 2024

作者： Zhao, Jianjun Liu, Haikun Zhang, Shuhao Duan, Zhuohui Liao, Xiaofei Jin, Hai Zhang, Yu School of Computer Science and Technology Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Wuhan China School of Computer Science and Engineering Nanyang Technological University Singapore

ISBN: (纸本)9798350317152

Transactional stream processing engines (TSPEs) have gained increasing attention due to their capability of processing real-time stream applications with transactional semantics. However, TSPEs remain susceptible to system failures and power outages. Existing TSPEs mainly focus on performance improvement, but still face a significant challenge to guarantee fault tolerance while offering high-performance services. We revisit commonly-used fault tolerance approaches in stream processing and database systems, and find that these approaches do not work well on TSPEs due to complex data dependencies. In this paper, we propose a novel TSPE called MorphStreamR to achieve fast failure recovery while guaranteeing low performance overhead at runtime. The key idea of MorphStreamR is to record intermediate results of resolved dependencies at runtime, and thus eliminate data dependencies to improve task parallelism during failure recovery. MorphStreamR further mitigates the runtime overhead by selectively tracking data dependencies and incorporating workload-aware log commitment. Experimental results show that MorphStreamR can significantly reduce the recovery time by up to 3.1 x while experiencing much less performance slowdown at runtime, compared with other applicable fault tolerance approaches. © 2024 IEEE.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

A Review of Knowledge Graph in Traditional Chinese Medicine:Analysis,Construction,Application and Prospects

引用

Computers, Materials & Continua 2024年第12期81卷 3583-3616页

作者： Xiaolong Qu Ziwei Tian Jinman Cui Ruowei Li Dongmei Li Xiaoping Zhang School of Information Science and Technology Beijing Forestry UniversityBeijing100083China National Data Center of Traditional Chinese Medicine China Academy of Chinese Medical SciencesBeijing100700China Engineering Research Center for Forestry-oriented Intelligent Information Processing of National Forestry and Grassland Administration Beijing Forestry UniversityBeijing100083China

As an advanced data science technology,the knowledge graph systematically integrates and displays the knowledge framework within the field of traditional Chinese medicine(TCM).This not only contributes to a deeper comprehension of traditional Chinese medical theories but also provides robust support for the intelligent decision systems and medical applications of *** this backdrop,this paper aims to systematically review the current status and development trends of TCM knowledge graphs,offering theoretical and technical foundations to facilitate the inheritance,innovation,and integrated development of ***,we introduce the relevant concepts and research status of TCM knowledge ***,we conduct an in-depth analysis of the challenges and trends faced by key technologies in TCM knowledge graph construction,such as knowledge representation,extraction,fusion,and reasoning,and classifies typical knowledge graphs in various subfields of ***,we comprehensively outline the current medical applications of TCM knowledge graphs in areas such as information retrieval,diagnosis,question answering,recommendation,and knowledge ***,the current research status and future directions of TCM knowledge graphs are concluded and *** believe this paper contributes to a deeper understanding of the research dynamics in TCM knowledge graphs and provides essential references for scholars in related fields.

关键词： Systematic review traditional Chinese medicine knowledge graph deep learning medical applications

来源：评论

学校读者我要写书评

暂无评论

research on Fault Diagnosis of Spacecraft Control System Based on Graph Neural Network 8

Research on Fault Diagnosis of Spacecraft Control System Bas...

引用

8th International Conference on intelligent computing and Signal Processing, ICSP 2023

作者： Ning, Zhicheng Liu, Xiaoxiang Li, Xinyuan Liu, Jun Beijing Insitute of Control Engineering Science and Technology on Space Intelligent Control Laboratory Beijing China Beijing University of Posts and Telecommunications Intelligent Perception and Computing Research Center Beijing China

ISBN: (纸本)9798350302455

The fault diagnosis technology of spacecraft control systems is a crucial component of spacecraft health management. Traditional fault diagnosis technologies, such as model-based diagnosis and signal processing, are relatively mature but are limited in their ability to fully utilize information in big data environments. Neural network-based fault diagnosis methods often overlook the sequential nature of spacecraft data as time series data. Given that the state of a spacecraft at any given time is closely related to preceding data, it is possible to conduct fault diagnosis by extracting relevant features from fault sample data. In this paper, we propose a graph neural network-based fault diagnosis method for spacecraft control systems. To address the issue of limited fault samples, we construct a spacecraft control system model and generate various types of gyro and flywheel fault data through fault injection. Utilizing the Graphstar model - a powerful graph neural network with strong information mining capabilities - we transform one-dimensional fault data into graph data with spatial structure and extract relevant characteristics through deep learning to diagnose faults. Simulation results demonstrate that our method can effectively diagnose faults with high accuracy. © 2023 IEEE.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Intersecting-Boundary-Sensitive Fingerprinting for Tampering Detection of DNN Models 41

Intersecting-Boundary-Sensitive Fingerprinting for Tampering...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Bai, Xiaofan He, Chaoxiang Ma, Xiaojing Zhu, Bin Benjamin Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China Microsoft United States School of Computer Science and Technology Huazhong University of Science and Technology China Cluster and Grid Computing Lab China

Cloud-based AI services offer numerous benefits but also introduce vulnerabilities, allowing for tampering with deployed DNN models, ranging from injecting malicious behaviors to reducing computing resources. Fingerprint samples are generated to query models to detect such tampering. In this paper, we present Intersecting-Boundary-Sensitive Fingerprinting (IBSF), a novel method for black-box integrity verification of DNN models using only top-1 labels. Recognizing that tampering with a model alters its decision boundary, IBSF crafts fingerprint samples from normal samples by maximizing the partial Shannon entropy of a selected subset of categories to position the fingerprint samples near decision boundaries where the categories in the subset intersect. These fingerprint samples are almost indistinguishable from their source samples. We theoretically establish and confirm experimentally that these fingerprint samples' expected sensitivity to tampering increases with the cardinality of the subset. Extensive evaluation demonstrates that IBSF surpasses existing state-of-the-art fingerprinting methods, particularly with larger subset cardinality, establishing its state-of-the-art performance in black-box tampering detection using only top-1 labels. The IBSF code is available at: https://***/CGCL-codes/IBSF. Copyright 2024 by the author(s)

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

Debiasing Computer Vision Models using data Augmentation based Adversarial Techniques 3

Debiasing Computer Vision Models using Data Augmentation bas...

引用

3rd Workshop on Bias, Risk, Ethical AI, Explainability and the Role of Logic and Logic Programming, BEWARE 2024

作者： Kumar, Teerath Mandal, Abhishek Leavy, Susan Little, Suzanne Mileo, Alessandra Bendechache, Malika CRT-AI School of Computing Dublin City University Dublin Ireland Insight SFI Research Center for Data Analytics School of Computing Dublin City University Dublin Ireland Insight SFI Research Center for Data Analytics School of Information and Communication Studies University College Dublin Dublin Ireland ADAPT & Lero Research Centres School of Computer Science University of Galway Galway Ireland

Deep learning models in computer vision, such as Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), have been found to exhibit significant biases related to factors such as gender and ethnicity. These biases often originate from inherent imbalances in training data predominantly sourced from the internet. In this study, we aim to address gender bias in computer vision models by curating a specialized dataset that highlights gender-related disparities. Additionally, we measure dataset diversity across six datasets (FFHQ, WIKI, IMDB, LFW, UTK Faces, diverse dataset), five professions (CEO, engineer, nurse, politician, and teacher) and different query retrieval tasks using the Image Similarity Score (ISS). To reduce learned gender biases and increase data diversity, we propose adversarial data augmentation techniques that specifically target facial regions within images. These techniques, named Partial Mix (PM), that partially mixes two gendered faces in a squared pattern, and Noise Addition (NA), that adds noise to the facial region, are designed to mitigate bias. Our experimental results demonstrate increased data diversity across the six datasets and professions, along with reduction in gender bias for CNN-based models. However, these adversarial techniques were less effective in reducing bias for Vision Transformers. This discrepancy highlights the unique challenges for bias mitigation posed by ViTs. Consistent with prior research, our findings indicate that ViTs learn from a broader set of visual cues compared to CNNs. This increased sensitivity makes ViTs more prone to amplifying biases, emphasizing the need for tailored bias mitigation strategies when deploying these models in real-world applications. © 2024 Copyright for this paper by its authors.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Multi-Intent Recognition with BERT Embeddings and Graph-based Decoding 22

Enhanced Multi-Intent Recognition with BERT Embeddings and G...

引用

22nd IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2024

作者： Cui, Mengmeng Zhang, Rui Xiang, Haolong Xue, Shengjun Nanjing University of Information Science and Technology Nanjing China Jiangsu Province Engineering Research Center of Advanced Computing and Intelligent Services Nanjing China Silicon Lake College Suzhou China

ISBN: (纸本)9798331509712

In the question-answering system, users frequently express multiple intents within a single utterance. The majority of intent recognition models tend to either primarily address single-intent scenarios or simply aggregate the overall intent context vectors of all tokens, neglecting the integration of multi-intent information. However, current methods suffer from slow inference speed, limited generalization capability, and the relatively independent treatment of multi-intent recognition tasks, leading to suboptimal model performance. In this paper, we design a novel model based on BERT, employing a non-autoregressive approach for the task of multi-intent recognition. This model achieves enhanced speed and accuracy. Additionally, this model introduces a global slot-intent interaction layer, simulating interactions between multiple intents and slots within an utterance. Experimental results on a series of benchmarking datasets demonstrate that this model outperforms the state-of-the-art methods, improving both the effectiveness and efficiency of the overall system. © 2024 IEEE.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

STB-GraCapsNet: A Novel Capsule Network Structure with Swin Transformer Block 25th

STB-GraCapsNet: A Novel Capsule Network Structure with Swin...

引用

25th International Conference on Parallel and Distributed computing, Applications and Technologies, PDCAT 2024

作者： Zhang, Chunying Dong, Ziao Wang, Liya Liu, Lu Ren, Jing Ma, Jiang Liu, Bin College of Science North China University of Science and Technology 21 Bohai Road Caofeidian Xincheng Hebei Tangshan063210 China Big data and Social Computing Research Center Hebei University of Science and Technology Hebei Shijiazhuang0500198 China

ISBN: (纸本)9789819642069

Capsule network is a new type of neural network encoding features into capsules and constructing the part-whole relationships, which demonstrated good performance in image classification. However, it has some issues such as weak feature extraction ability and large number of training parameters, leading to performance decline when processing images with complex background. To address these issues, this article proposes a novel capsule network structure called STB-GraCapsNet, with key improvements as follows: 1) It uses Swin Transformer Block with the shift window attention mechanism for data preprocessing to obtain richer features;2) the features are then processed through Linear Embedding and passed into the Primary Capsule Layer to generate high-dimension feature capsules, which reduces primary capsules number and improves feature extraction ability of the network. Ablation and comparative experiments based on multiple datasets show that STB-GraCapsNet performs better on complex datasets: 77.8% and 36.2% reduction in parameters number of capsule structure, and 12.07% and 5.22% improvement in model accuracy, as compared to CapsNet and GraCapsNet, respectively. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Chatbots and EFL Learning: A Systematic Review

Chatbots and EFL Learning: A Systematic Review

引用

2024 Joint of International Conference on Learning Analytics and Knowledge Workshops, LAK-WS 2024

作者： Woollaston, Steve Flanagan, Brendan Ogata, Hiroaki Graduate School of Social Informatics Kyoto University Kyoto Japan Center for Innovative Research and Education in Data Science Kyoto University Japan Academic Center for Computing and Media Studies Kyoto University Kyoto Japan

Chatbots have been increasingly playing a greater role in English as a foreign language education, offering learners the opportunity to practise with a conversational agent at any time and in different contexts. To grasp how this field has developed and identify emerging trends and opportunities, we conducted a systematic bibliometric analysis of research on chatbots in English language learning from 2006 to 2023. The analysis highlights the increasing importance of Large Language Models in language learning, exploring their potential to overcome previous limitations of chatbot technology. The implications of these findings for future research are discussed, particularly the potential for chatbot designs tailored to the specific needs of English language learners. © 2024 CEUR-WS. All rights reserved.

关键词： Speech processing

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Dual-Manifold Regularized Fuzzy Broad Learning for ICU Admission Prediction in Post-COVID Transplant Recipients

Semi-Supervised Dual-Manifold Regularized Fuzzy Broad Learni...

引用

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

作者： Xiao Zhang Àngela Nebot Soft Computing Research Group Intelligent Data Science and Artificial Intelligence Research Center Universitat Politècnica de Catalunya Barcelona Spain

ISBN: (数字)9798350319545

ISBN: (纸本)9798350319552

This paper introduces a novel semi-supervised Dual-Manifold Regularized Fuzzy Broad Learning System (DMR-FBLS) designed for predicting intensive care unit (ICU) admissions among post-COVID organ transplant recipients. Addressing the challenge of increased mortality risk and strained medical resources among patients who are COVID-19-infected transplant recipients, our study fills the gap by employing machine learning to predict the ICU requirements for this particular group of patients. The DMR-FBLS uniquely integrates two manifold regularizations—feature and sample manifold regularization—into the fuzzy broad learning system (FBLS) framework. This integration enhances the system's capacity to utilize the latent structural relationships within the data. Evaluated using the IDOTCOVID database, the DMR-FBLS demonstrated superior performance over other models in terms of accuracy, F1-score, and G-mean. In scenarios with limited sample availability, DMR-FBLS outperformed both the FBLS and TSK fuzzy systems in terms of accuracy and G-mean. This underscores the efficacy of DMR-FBLS as a semi-supervised learning fuzzy system, accurately predicting ICU demands and thereby providing decision support for medical professionals in optimizing resource allocation for transplant patients.

关键词： Manifolds Accuracy databases Decision making Machine learning Semisupervised learning Organ transplantation

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：