检索结果-内蒙古大学图书馆

Multi-View Attributed Graph clustering

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2023年第2期35卷 1872-1880页

作者： Lin, Zhiping Kang, Zhao Zhang, Lizong Tian, Ling Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 611731 Peoples R China

Multi-view graph clustering has been intensively investigated during the past years. However, existing methods are still limited in two main aspects. On the one hand, most of them can not deal with data that have both attributes and graphs. Nowadays, multi-view attributed graph data are ubiquitous and the need for effective clustering methods is growing. On the other hand, many state-of-the-art algorithms are either shallow or deep models. Shallow methods may seriously restrict their capacity for modeling complex data, while deep approaches often involve large number of parameters and are expensive to train in terms of running time and space needed. In this paper, we propose a novel multi-view attributed graph clustering (MAGC) framework, which exploits both node attributes and graphs. Our novelty lies in three aspects. First, instead of deep neural networks, we apply a graph filtering technique to achieve a smooth node representation. Second, the original graph could be noisy or incomplete and is not directly applicable, thus we learn a consensus graph from data by considering the heterogeneous views. Third, high-order relations are explored in a flexible way by designing a new regularizer. Extensive experiments demonstrate the superiority of our method in terms of effectiveness and efficiency.

关键词： clustering methods Sparse matrices Data models clustering algorithms Task analysis Symmetric matrices Motion pictures Multi-view clustering multiplex network heterogeneous graph high-order information multi-layer networks

来源：评论

学校读者我要写书评

暂无评论

A Game-Based Evolutionary clustering With Historical Information Aggregation for Personal Recommendation

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2023年第2期7卷 552-564页

作者： Chen, Jianrui Zhu, Tingting Gong, Maoguo Wang, Zhihui Minist Culture & Tourism Key Lab Intelligent Comp & Serv Technol Folk Song Xian Peoples R China Shaanxi Normal Univ Sch Comp Sci Xian 710119 Peoples R China Xidian Univ Minist Educ Key Lab Intelligent Percept & Image Understanding Sch Elect Engn Xian 710071 Peoples R China

In order to alleviate the network information overload, recommender system becomes widespread in personalized recommendation. However, due to the increase of the number of users and items in the network, the rating data gets increasingly sparse. At this time, it is necessary to use a variety of clustering algorithms to divide nodes into different communities, and then make recommendations in each community, which can improve the performance of recommendations and reduce the time complexity of algorithms. In this paper, we propose a game-based evolutionary clustering with historical information aggregation for personal recommendation. Firstly, a payoff function of game theory is introduced into the evolutionary clustering to accelerate the stability of the algorithm. In this clustering approach, the next state value of each node is related not only to the current state value, but also to the historical states, hence, it achieve better prediction results. Meanwhile, the clustering method is theoretically proved to be stable by Lyapunov stability theory. And then, we predict the possible ratings by the user-based collaborate filtering method, and recommend items for target users according to the preferences of neighbors. Finally, diverse experiments are executed on seven real recommendation datasets to verify our recommendation results are better than several compared algorithms.

关键词： clustering algorithms Heuristic algorithms Mathematical models Prediction algorithms Game theory Recommender systems Computational modeling Evolutionary clustering game theory historical information aggregation collaborative filtering recommendation

来源：评论

学校读者我要写书评

暂无评论

Multiple Kernel clustering With Compressed Subspace Alignment

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023年第1期34卷 252-263页

作者： Zhou, Sihang Ou, Qiyuan Liu, Xinwang Wang, Siqi Liu, Luyan Wang, Siwei Zhu, En Yin, Jianping Xu, Xin Natl Univ Def Technol Coll Intelligence Sci & Technol Changsha 410073 Peoples R China Natl Univ Def Technol Sch Comp Sci Changsha 410073 Peoples R China Tencent Jarvis Lab Shenzhen 518057 Peoples R China Dongguan Univ Technol Sch Cyberspace Sci Dongguan 523808 Guangdong Peoples R China

Multiple kernel clustering (MKC) has recently achieved remarkable progress in fusing multisource information to boost the clustering performance. However, the O( n(2)) memory consumption and O( n(3) ) computational complexity prohibit these methods from being applied into median- or large-scale applications, where n denotes the number of samples. To address these issues, we carefully redesign the formulation of subspace segmentation-based MKC, which reduces the memory and computational complexity to O( n) and O( n(2) ), respectively. The proposed algorithm adopts a novel sampling strategy to enhance the performance and accelerate the speed of MKC. Specifically, we first mathematically model the sampling process and then learn it simultaneously during the procedure of information fusion. By this way, the generated anchor point set can better serve data reconstruction across different views, leading to improved discriminative capability of the reconstruction matrix and boosted clustering performance. Although the integrated sampling process makes the proposed algorithm less efficient than the linear complexity algorithms, the elaborate formulation makes our algorithm straightforward for parallelization. Through the acceleration of GPU and multicore techniques, our algorithm achieves superior performance against the compared state-of-the-art methods on six datasets with comparable time cost to the linear complexity algorithms.

关键词： Kernel clustering algorithms Prediction algorithms Partitioning algorithms Optimization Memory management Sparse matrices Compressed subspace alignment multiple kernel clustering (MKC) sampling process modeling

来源：评论

学校读者我要写书评

暂无评论

FedLC: Optimizing Federated Learning in Non-IID Data via Label-Wise clustering

引用

IEEE ACCESS 2023年 11卷 42082-42095页

作者： Lee, Hunmin Seo, Daehee Univ Minnesota Dept Comp Sci Minneapolis MN 55455 USA Sangmyung Univ Dept Artificial Intelligence & Data Engn Seoul 03016 South Korea

As contemporary systems are being operated in dynamic situations alternating into decentralized and distributed environments from conventional centralized frameworks, Federated Learning (FL) has been gaining attention for an effective architecture when aggregating the information and correspondingly trained AI model of geographically distributed datasets. However, the convergence of FL suffers from the skewed and biased non-IID local dataset acquired from the heterogeneous environment, which is common in real-world practice. To address this issue, we propose a novel Label-wise clustering algorithm in FL (FedLC) that guarantees the convergence among local clients that hold unique distribution. We theoretically analyze the non-IID attributes that potentially affect the performance, defining the six non-IID scenarios in hierarchical order. Through conducting experiments on the suggested non-IID scenarios, we empirically show that the vanilla FL aggregation model is incapable of gaining stable convergence, generating a biased model. By pre-evaluating the local dataset prior to training models, FedLC determines the potential contributions with respect to trainability in a global view, and adaptively selects the locals to collaboratively take part in while aggregation. Our experimental results show that the FedLC outperforms the state-of-the-art non-IID FL optimization studies, offering a robust convergence in a highly skewed and biased non-IID dataset.

关键词： Convergence Training clustering algorithms Adaptation models Federated learning Optimization Computer architecture Convergence optimization in federated learning federated learning in heterogenous and non-IID dataset label-wise clustering

来源：评论

学校读者我要写书评

暂无评论

Centroid Based Celestial clustering Algorithm: A Novel Unsupervised Learning Method for Haemogram Data clustering

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2023年第3期7卷 942-956页

作者： Kumar, Shibu K. B. Samuel, Philip Coll Engn Trivandrum Dept Comp Sci & Engn Trivandrum 695016 Kerala India Cochin Univ Sci & Technol Dept Comp Sci Cochin 682022 Kerala India

Accuracy of clustering is the most important parameter as far as automated disease identification is concerned. There have always been attempts to automate the process of disease prediction from haemogram data. However, there are several components in blood test results and very often we find that a variety of combinations of these component results are to be used to detect a disease. This makes identification of diseases really hard and necessitates the use of data analysis techniques. As new diseases are arising from time to time, a useful method for prediction is unsupervised learning and the corresponding data analysis technique is clustering. An easy, efficient and centroid based clustering algorithm that has been in practice widely is k-means. Its simplicity and efficiency make it a natural choice for most of the clustering applications. However, k-means is largely dependent on the selection of initial cluster centers and a bad choice can make it fall to local optima, thereby sacrificing accuracy. Besides, it is non-deterministic in nature. This paper proposes a novel, nature inspired, clustering method, named Centroid Based Celestial clustering, which overcomes the above issues. Our method is deterministic and converges to global optima on spherical datasets. We experimentally evaluate our algorithm for speed of execution and cluster quality against well-known clustering algorithms using statistical evaluation metrics like silhouette width, adjusted rand index and Dunn index. We use the method to predict diseases identifiable from blood tests and our experiments show that the accuracy of prediction is very promising.

关键词： Diseases clustering algorithms Prediction algorithms Blood Optimization Force Unsupervised learning Centroid based celestial clustering clustering algorithms disease prediction haemogram data clustering nature inspired methods

来源：评论

学校读者我要写书评

暂无评论

A Data Deduplication Scheme Based on DBSCAN With Tolerable clustering Deviation

引用

IEEE ACCESS 2023年 11卷 9742-9750页

作者： Teng, Yan Xian, Hequn Lu, Quanli Guo, Feng Qingdao Univ Coll Comp Sci & Technol Qingdao 266071 Peoples R China Chinese Acad Sci Inst Informat Engn State Key Lab Informat Secur Beijing 100093 Peoples R China Shandong Zhengzhong Informat Technol Co Ltd Jinan 250014 Peoples R China Shandong Digital Appl Sci Res Inst Co Ltd Jinan 250101 Peoples R China

To protect data privacy, users prefer to store encrypted data in cloud servers. Cloud servers reduce the cost of storage and network bandwidth by eliminating duplicate copies. To address the potential internal data leakage problem, the concept of clustering deviation is proposed for the first time. We improve the DBSCAN algorithm to tolerate clustering deviation. A data deduplication scheme is built upon the new algorithm, which considers users as clustering samples. Instead of immediately re-clustering new users, a certain deviation is tolerated to assign the users to the existing classes. We determine the popularity of the data according to user clustering results and apply different encryption schemes to protect the security of unpopular data more effectively. The performance of the algorithm is analyzed and compared with other methods through experiments, and the results verify the feasibility and efficiency of the proposed deduplication scheme.

关键词： Encryption clustering algorithms Servers Cloud computing Machine learning algorithms Heuristic algorithms Data privacy Deduplication cloud storage data popularity DBSCAN

来源：评论

学校读者我要写书评

暂无评论

End-to-End Supervised Hierarchical Graph clustering for Speaker Diarization

引用

IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2025年 33卷 448-457页

作者： Singh, Prachi Ganapathy, Sriram Indian Inst Sci Dept Elect Engn Learning & Extract Acoust Patterns Lab Bangalore 560012 India

Speaker diarization, the task of segmenting an audio recording based on speaker identity, constitutes an important speech pre-processing step for several downstream applications. The conventional approach to diarization involves multiple steps of embedding extraction and clustering, which are often optimized in an isolated fashion. While end-to-end diarization systems attempt to learn a single model for the task, they are often cumbersome to train and require large supervised datasets. In this paper, we propose an end-to-end supervised hierarchical clustering algorithm based on graph neural networks (GNN), called End-to-end Supervised HierARchical clustering (E-SHARC). The embedding extractor is initialized using a pre-trained x-vector model while the GNN model is trained initially using the x-vector embeddings from the pre-trained model. Finally, the E-SHARC model uses the front-end mel-filterbank features as input and jointly optimizes the embedding extractor and the GNN clustering module, performing representation learning, metric learning, and clustering with end-to-end optimization. Further, with additional inputs from an external overlap detector, the E-SHARC approach is capable of predicting the speakers in the overlapping speech regions. The experimental evaluation on benchmark datasets like AMI, Voxconverse and DISPLACE, illustrates that the proposed E-SHARC framework provides competitive diarization results using graph based clustering methods.

关键词： Graph neural networks Recording Feature extraction Measurement Image edge detection clustering algorithms Training Nearest neighbor methods Voice activity detection Symbols overlap speech processing speaker diarization supervised hierarchical clustering

来源：评论

学校读者我要写书评

暂无评论

Harris Hawks Optimization-Based clustering Algorithm for Vehicular Ad-Hoc Networks

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2023年第6期24卷 5822-5841页

作者： Ali, Asad Aadil, Farhan Khan, Muhammad Fahad Maqsood, Muazzam Lim, Sangsoon Univ Engn & Technol Peshawar Dept Comp Sci & Informat Technol Peshawar 25000 Pakistan COMSATS Univ Islamabad Comp Sci Dept Attock Campus Attock 43600 Pakistan Sungkyul Univ Dept Comp Engn Anyang 14097 South Korea

Vehicular ad-hoc network (VANET) is highly dynamic due to the high speed and sparse distribution of vehicles on the road. This creates major challenges (e.g., network fragmentation, packet routing) for the researchers to enable robust, reliable, and scalable communication, especially in a highly dense network. clustering in VANET is one of the remedies to address the scalability issue. However, it is observed in the literature, that existing clustering techniques produce a high number of clusters for the vehicular environment. Consequently, it increases the consumption of scarce resources in a wireless network. Furthermore, it also increases the communication overhead as well as the number of hops for data routing. As a result communication latency also increases and the reliability of communication protocol decreases. So it is highly desirable to find out the optimal clusters for a given vehicular environment. As finding optimal clusters is a multi-objective combinatorial optimization problem, therefore by employing nature-inspired meta-heuristic algorithms we can optimize the multi-objective problem. To this end, we proposed a novel clustering algorithm based on the Harris Hawks Optimization (HHO) algorithm for VANET (HHOCNET). HHO algorithm is a nature-inspired meta-heuristic algorithm inspired by the foraging maneuver of hawks called surprise pounce. The proposed framework imitates the cooperative foraging maneuver of hawks (i.e., surprise pounce for creating optimized vehicular clusters). The stochastic operators of the HHO algorithm and proper maintenance of the equilibrium state between the operations of exploration and exploitation enable the proposed algorithm to escape from the local optima and provide a globally optimal solution (i.e., the optimal number of vehicular clusters). Simulations are performed in MATLAB and the results are compared with the state-of-art schemes (i.e., Gray Wolf optimization-based clustering algorithm (GWOCNET), Multi-objective P

关键词： clustering algorithms Vehicular ad hoc networks Metaheuristics Ad hoc networks Reliability Wireless communication Safety Intelligent clustering VANET clustering intelligent transportation System cluster optimization

来源：评论

学校读者我要写书评

暂无评论

RoCaSH2: An Effective Route clustering and Search Heuristic for Large-Scale Multi-Depot Capacitated Arc Routing Problem

引用

IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE 2023年第4期18卷 43-56页

作者： Zhang, Yuzhou Mei, Yi Zhang, Haiqi Cai, Qinghua Wu, Haifeng Nanjing Xiaozhuang Univ Nanjing Peoples R China Victorial Univ Wellington Wellington New Zealand Nanjing Univ Sci & Technol Nanjing Peoples R China Anqing Normal Univ Anqing Anhui Peoples R China

The Multi-Depot Capacitated Arc Routing Problem (MDCARP) is an important combinatorial optimization problem with wide applications in logistics. Large Scale MDCARP (LSMDCARP) often occurs in the real world, as the problem size (e.g., number of edges/tasks) is usually very large in practice. It is challenging to solve LSMDCARP due to the large search space and complex interactions among the depots and the tasks. Divide-and-conquer strategies have shown success in solving large-scale problems by decomposing the problem into smaller sub-problems to be solved separately. However, it is challenging to find accurate decomposition for LSMDCARP. To address this issue and alleviate the negative effect of inaccurate problem decomposition, this article proposes a new divide-and-conquer strategy for solving LSMDCARP, which introduces a new restricted global optimization stage within the typical dynamic decomposition procedure. Based on the new divide-and-conquer strategy, this article develops a problem-specific Task Moving among Sub-problems (TMaS) process for the global optimization stage and incorporates it into the state-of-the-art RoCaSH algorithm for LSMDCARP. The resultant algorithm, namely, RoCaSH2, was compared with the state-of-the-art algorithms on a wide range of LSMDCARP instances, and the results showed that RoCaSH2 can achieve significantly better results than the state-of-the-art algorithms within a much shorter time.

关键词： Heuristic algorithms clustering algorithms Routing Search problems Task analysis Optimization Logistics Artificial intelligence Complexity theory

来源：评论

学校读者我要写书评

暂无评论

FMvC: Fast Multi-View clustering

引用

IEEE ACCESS 2023年 11卷 12807-12819页

作者： Wang, Jiada Liu, Yijun Ye, Wujian Guangdong Univ Technol Sch Informat Engn Guangzhou Peoples R China Guangdong Univ Technol Res Inst IC Innovat Guangzhou Peoples R China

In multi-view clustering, an eigen-decomposition of the Laplacian matrix of the graph is usually necessary. This leads to a significant increase in time cost and also requires post-processing such as $k$ -means. In addition, some methods require learning a uniform graph matrix. In large-scale data, this process significantly increase time and memory costs. To address these problems, this paper proposes Fast Multi-view clustering (FMvC). First, non-negative constraints are added to the objective function from the unified view of relaxed normalized and ratio cuts. Then, graph reconstruction is performed on the similarity matrix using an indication matrix to ensure that the obtained graph has robust intra-cluster and weak inter-cluster connectivity. Besides, the operation speed of the method can be further enhanced by setting a common labeling matrix. Finally, the problem is solved optimally based on the strategy of alternating directional multipliers. Experimental results on eight real-world datasets demonstrate the effectiveness of the proposed algorithm, which can always outperform eleven existing baseline algorithms.

关键词： Matrix decomposition Linear programming Laplace equations clustering methods Costs clustering algorithms Sparse matrices Fast clustering multi-view clustering structured graph unified label matrix

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：