检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2708-2722页

作者： Xiang, Guodu Wang, Hao Yu, Kui Guo, Xianjie Cao, Fuyuan Song, Yukun Hefei University of Technology Key Laboratory of Knowledge Engineering with the Big Data of Ministry of Education Hefei230601 China Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China Shanxi University School of Computer and Information Technology Taiyuan030006 China

Learning causal structures from observational data is critical for causal discovery and many machine learning tasks. Traditional constraint-based methods first adopt conditional independence (CI) tests to learn a global skeleton layer by layer and then orient the undirected edges to obtain a causal structure. However, the reliability of these statistical tests largely depends on the quality of data samples. In real-life scenarios, the presence of data noise or limited samples often makes many CI tests unreliable at each layer in the skeleton learning phase, leading to an inaccurate skeleton. As the number of layers increases, the inaccurate skeleton will continue to impair the skeleton construction of subsequent layers. Furthermore, an unreliable skeleton hampers the skeleton orientation procedure, resulting in an unsatisfactory causal structure. In this article, we propose a Bootstrap-based layerwise refining (BLR) algorithm for causal structure learning, which includes two new procedures to solve the above problems. First, BLR utilizes a novel layerwise skeleton refining procedure to construct the global skeleton layer by layer based on the bootstrap sampling. Second, BLR employs a collective skeleton orientation procedure that incorporates scoring techniques to collectively orient the global skeleton. The experimental results show that BLR outperforms the state-of-the-art methods on the benchmark Bayesian Network datasets. © 2020 IEEE.

关键词： Refining

来源：评论

学校读者我要写书评

暂无评论

A novel hybrid butterfly optimization algorithm for feature selection with sine cosine velocity in the high-dimensional classification data

引用

Journal of Intelligent and Fuzzy Systems 2024年第5-6期47卷 369-391页

作者： Zhang, Li Chen, Xiaobo Key Laboratory of Data Science and Intelligence Education Hainan Normal University Ministry of Education Haikou Hainan China School of Computer Engineering Jiangsu University of Technology Changzhou Jiangsu China Changzhou City Center Branch People's Bank of China Changzhou Jiangsu China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun China

Aiming at the shortcomings of the traditional butterfly optimization algorithm in solving the high-dimensional classification feature selection problem, which has low convergence and is prone to fall into local optimal solutions, a new hybrid butterfly optimization algorithm is proposed, i.e., HBOA-SCV (A novel hybrid butterfly optimization algorithm with sine cosine velocity). The algorithm is applied to solve a high-dimensional classification feature selection problem. Firstly, the algorithm's global exploration and local exploitation ability can be dynamically balanced by introducing inertia weight coefficients w based on multiple learning strategies. Secondly, using the updated speed position formula of the sine-cosine acceleration strategy, individual butterflies' autonomous search ability and convergence speed can be further improved. Finally, according to the fitness value of each butterfly individual, the moving step length and direction of the butterfly individual are automatically adjusted better to fit the actual search process of the butterfly individual, increase the search ability in the global range, and avoid the algorithm from falling into the local optimum. To verify the algorithm's effectiveness, 18 high-dimensional classification numbers are selected to carry out simulation and comparison experiments between HBOA-SCV and traditional BOA algorithm, five improved BOA algorithms and other comparative algorithms for high-dimensional classification data successively. The experimental results show that the average fitness value and classification accuracy of the HBOA-SCV algorithm are better than the comparison algorithm, thus verifying the superiority of the HBOA-SCV algorithm. © 2024 - IOS Press. All rights reserved.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Joint user profiling with hierarchical attention networks

引用

Frontiers of Computer Science 2023年第3期17卷 133-143页

作者： Xiaojian LIU Yi ZHU Xindong WU Key Laboratory of Knowledge Engineering with Big Data(Hefei University of Technology) Ministry of EducationHefei 230009China School of Computer Science and Information Engineering Hefei University of TechnologyHefei 230009China School of Information Engineering Yangzhou UniversityYangzhou 225009China Mininglamp Academy of Sciences MininglampBeijing 100193China

User profiling by inferring user personality traits,such as age and gender,plays an increasingly important role in many real-world *** existing methods for user profiling either use only one type of data or ignore handling the noisy information of ***,they usually consider this problem from only one *** this paper,we propose a joint user profiling model with hierarchical attention networks(JUHA)to learn informative user representations for user *** JUHA method does user profiling based on both inner-user and inter-user *** explore inner-user features from user behaviors(e.g.,purchased items and posted blogs),and inter-user features from a user-user graph(where similar users could be connected to each other).JUHA learns basic sentence and bag representations from multiple separate sources of data(user behaviors)as the first round of data *** this module,convolutional neural networks(CNNs)are introduced to capture word and sentence features of age and gender while the self-attention mechanism is exploited to weaken the noisy *** this,we build another bag which contains a user-user ***-user features are learned from this bag using propagation information between linked users in the *** acquire more robust data,inter-user features and other inner-user bag representations are joined into each sentence in the current bag to learn the final bag ***,all of the bag representations are integrated to lean comprehensive user representation by the self-attention *** experimental results demonstrate that our approach outperforms several state-of-the-art methods and improves prediction performance.

关键词： user profiling hierarchical attention joint learning inner-user feature inter-user feature

来源：评论

学校读者我要写书评

暂无评论

Ensemble Learning Based Employment Recommendation Under Interaction Sparsity for College Students 9th

Ensemble Learning Based Employment Recommendation Under Inte...

引用

19th International Conference on Advanced data Mining and Applications, ADMA 2023

作者： Zhu, Haiping Zhao, Yifei Wu, Yuchen Chen, Yan Li, Wenhao Zheng, Qinghua Tian, Feng Department of Computer Science and Technology Xi’an Jiaotong University Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an China

ISBN: (纸本)9783031466632

Recommendation systems play a crucial role in helping college students find job opportunities. However, the sparsity of interactions in employment recommendation for college students poses a challenge for models based on historical user preferences. To address this issue, we propose a novel model called Ensemble Learning based Employment Recommendation under Interaction Sparsity for College Students (EERIS). The model comprises two components: a similarity information component that uses pooled users to determine the nearest neighbor in user similarity measurement, and a global interaction component that uses interaction vectors of user groups to enhance interactions. To evaluate the missing interactions, we propose a loss function called CellLoss. These components are combined based on ensemble learning to improve the model’s generalization and scalability. Our experiments on two real-world datasets demonstrate the superior performance of the EERIS model. Ablation experiments further confirm that each component positively contributes to the model’s performance. Additionally, we design a revised metric for better model testing. Overall, the proposed EERIS model effectively addresses the interaction sparsity in employment recommendation for college students and provides satisfactory recommendations to students. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

NI-GDBA: Non-Intrusive Distributed Backdoor Attack Based on Adaptive Perturbation on Federated Graph Learning 25

NI-GDBA: Non-Intrusive Distributed Backdoor Attack Based on ...

引用

34th ACM Web Conference, WWW 2025

作者： Li, Ken Shi, Bin Wei, Jiazhe Dong, Bo School of Computer Science and Technology Xi’an Jiaotong University Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi’an China School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an China School of Distance Education Xi’an Jiaotong University Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an China

ISBN: (纸本)9798400712746

Federated Graph Learning (FedGL) is an emerging Federated Learning (FL) framework that learns the graph data from various clients to train better Graph Neural Networks(GNNs) model. Owing to concerns regarding the security of such framework, numerous studies have attempted to execute backdoor attacks on FedGL, with a particular focus on distributed backdoor attacks. However, all existing methods posting distributed backdoor attack on FedGL only focus on injecting distributed backdoor triggers into the training data of each malicious client, which will cause model performance degradation on original task and is not always effective when confronted with robust federated learning defense algorithms, leading to low success rate of attack. What’s more, the backdoor signals introduced by the malicious clients may be smoothed out by other clean signals from the honest clients, which potentially undermining the performance of the attack. To address the above significant shortcomings, we propose a non-intrusive graph distributed backdoor attack(NI-GDBA) that does not require backdoor triggers to be injected in the training data. Our attack trains an adaptive perturbation trigger generator model for each malicious client to learn the natural backdoor from the GNN model downloading from the server with the malicious client’s local data. In contrast to traditional distributed backdoor attacks on FedGL via trigger injection in training data, our attack on different datasets such as Molecules and Bioinformatics have higher attack success rate, stronger persistence and stealth, and has no negative impact on the performance of the global GNN model. We also explore the robustness of NI-GDBA under different defense strategies, and based on our extensive experimental studies, we show that our attack method is robust to current federated learning defense methods, thus it is necessary to consider non-intrusive distributed backdoor attacks on FedGL as a novel threat that requires custom d

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Multicomponent Similarity Graphs for Cross-Network Node Classification

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第3期5卷 1411-1424页

作者： Zhang, Yuhong Shi, Congmei Li, Xinzheng Zhang, Zan Hu, Xuegang School of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230088 China Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Ministry of Education Hefei230009 China

Cross-network node classification aims to train a classifier for an unlabeled target network using a source network with rich labels. In applications, the degree of nodes mostly conforms to the long-tail distribution, i.e., most nodes in the network are tail nodes with sparse neighborhoods. The established methods focus on either the discrepancy cross network or the long tail in a single network. As for the cross-network node classification under long tail, the coexistence of sparsity of tail nodes and the discrepancy cross-network challenges existing methods for long tail or methods for the cross-network node classification. To this end, a multicomponent similarity graphs for cross-network node classification (MS-CNC) is proposed in this article. Specifically, in order to address the sparsity of the tail nodes, multiple component similarity graphs, including attribute and structure similarity graphs, are constructed for each network to enrich the neighborhoods of the tail nodes and alleviate the long-tail phenomenon. Then, multiple representations are learned from the multiple similarity graphs separately. Based on the multicomponent representations, a two-level adversarial model is designed to address the distribution difference across networks. One level is used to learn the invariant representations cross network in view of structure and attribute components separately, and the other level is used to learn the invariant representations in view of the fused structure and attribute graphs. Extensive experimental results show that the MS-CNC outperforms the state-of-the-art methods. Impact Statement-Node classification is an important task in graph mining. With the unavailability of labels, some researchers propose cross-network node classification, using one labeled network to assist the node classification of another unlabeled network. However, the long-tail of nodes leads to unsatisfactory performance and challenges the recent cross-network node classification m

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

MacroTrend: A Write-Efficient Cache Algorithm for NVM-Based Read Cache

引用

Journal of Computer Science & Technology 2022年第1期37卷 207-230页

作者： Ning Bao Yun-Peng Chai Xiao Qin Chuan-Wen Wang Key Laboratory of Data Engineering and Knowledge Engineering Ministry of EducationBeijing 100872China School of Information Renmin University of ChinaBeijing 100872China Samuel Ginn College of Engineering Auburn UniversityAlabama 36830U.S.A.

The future storage systems are expected to contain a wide variety of storage media and layers due to the rapid development of NVM(non-volatile memory)*** NVM-based read caches,many kinds of NVM devices cannot stand frequent data updates due to limited write endurance or high energy consumption of ***,traditional cache algorithms have to update cached blocks frequently because it is difficult for them to predict long-term popularity according to such limited information about data blocks,such as only a single value or a queue that reflects frequency or *** this paper,we propose a new MacroTrend(macroscopic trend)prediction method to discover long-term hot blocks through blocks'macro trends illustrated by their access count *** then a new cache replacement algorithm is designed based on the MacroTrend prediction to greatly reduce the write amount while improving the hit *** conduct extensive experiments driven by a series of real-world traces and find that compared with LRU,MacroTrend can reduce the write amounts of NVM cache devices significantly with similar hit ratios,leading to longer NVM lifetime or less energy consumption.

关键词： non-volatile memory(NVM) solid state disk(SSD) cache endurance

来源：评论

学校读者我要写书评

暂无评论

Online Streaming Features Causal Discovery Algorithm Based on Partial Rank Correlation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第1期4卷 197-208页

作者： Yang, Jing Jiang, Liufeng Shen, Anbo Wang, Aiguo Key Laboratory of Knowledge Engineering with Big Data of Ministry of Education Hefei University of Technology Hefei230009 China School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China School of Electronic and Information Engineering Foshan University Foshan528011 China

Aimedat the problem of dynamic causal discovery in the era of artificial intelligence, this article combines partial rank correlation coefficients and streaming features in the field of Bayesian network structure learning and proposes a new online streaming feature causal discovery algorithm based on partial rank correlation named the partial rank casual discovery streaming feature based algorithm. This algorithm is not only suitable for Bayesian causal structure learning in dynamic feature spaces generated by sequential streams of features but can also effectively process multivariate linear Gaussian and nonlinear non-Gaussian data. We present three main contributions. First, for arbitrarily distributed datasets, which can be generated by the additive noise model, we proved that the partial rank correlation coefficient can be used as the criterion for the conditional independence test and explored the distribution of corresponding statistics. Second, the PCSDSF algorithm redefined the relevance based on partial rank statistic prospects and then redefined conditional dependence or independence. This method can significantly reduce the number of conditional independence tests and achieves a good time performance. Finally, theoretical analysis and several experiments proved the reliability of the algorithm. A simulation showed that on average, the PCSDSF algorithm outperforms existing algorithms in terms of both the accuracy and time performance. © 2022 IEEE.

关键词： Additive noise

来源：评论

学校读者我要写书评

暂无评论

EEG-Based Joint Semi-supervised Learning for Major Depressive Disorder Detection 26th

EEG-Based Joint Semi-supervised Learning for Major Depressi...

引用

26th International Conference on Pattern Recognition, ICPR 2022

作者： Chen, Tao Zheng, Tong Shi, Jinlong Guo, Yanrong Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei China

ISBN: (纸本)9783031376597

Major Depressive Disorder (MDD) has been a major mental disease in recent years, imposing huge negative impacts on both our society and individuals. The current clinical MDD detection methods, such as self-report scales and interviews, often suffer from their subjectiveness. In contrast, electroencephalography (EEG) signals reflect brain activity and can be used as an effective information source for MDD detection. However, the learning-based MDD detection methods with EEG data usually neglect the valuable information contained in the unlabeled data, therefore possibly suffering from the label scarcity issue. In this context, we propose a simple EEG-based Joint Semi-supervised Learning (JSL) model for the MDD detection task, which fully leverages the information from unlabeled data. Specifically, by equipping the unlabeled samples with the intermediately predicted pseudo labels, the accurate position of the class-specific centroids in the feature space can be gradually refined. Based on that, the auxiliary labels based on a heuristic centroid-based classifier can be obtained, which plays an effective complementary role in predicting the sample labels. The experiments on a public dataset demonstrate the effectivenes s of our method, showing an obvious performance gain via using the proposed semi-supervised strategy. © 2023, Springer Nature Switzerland AG.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

FOSS: A Self-Learned Doctor for Query Optimizer 40

FOSS: A Self-Learned Doctor for Query Optimizer

引用

40th IEEE International Conference on data engineering, ICDE 2024

作者： Zhong, Kai Sun, Luming Ji, Tao Li, Cuiping Chen, Hong Renmin University of China China Key Laboratory of Data Engineering and Knowledge Engineering MOE China Shanghai Yunxi Technology Co. Ltd. China Engineering Research Center of Database and Business Intelligence MOE China

ISBN: (纸本)9798350317152

Various works have utilized deep learning to address the query optimization problem in database system. They either learn to construct plans from scratch in a bottom-up manner or steer the plan generation behavior of traditional optimizer using hints. While these methods have achieved some success, they face challenges in either low training efficiency or limited plan search space. To address these challenges, we introduce FOSS, a novel framework for query optimization based on deep reinforcement learning. FOSS initiates optimization from the original plan generated by a traditional optimizer and incrementally refines suboptimal nodes of the plan through a sequence of actions. Additionally, we devise an asymmetric advantage model to evaluate the advantage between two plans. We integrate it with a traditional optimizer to form a simulated environment. Leveraging this simulated environment, FOSS can bootstrap itself to rapidly generate a large amount of high-quality simulated experiences. FOSS then learns from these experiences to improve its optimization capability. We evaluate the performance of FOSS on Join Order Benchmark, TPC-DS, and Stack Overflow. The experimental results demonstrate that FOSS outperforms the state-of-the-art methods in terms of latency performance. Compared to PostgreSQL, FOSS achieves speedup ranging from 1.15x to 8.33x in total latency across different benchmarks. © 2024 IEEE.

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：