Self-Grouping Multi-network Clustering

Ni, Jingchao; Cheng, Wei; Wang, Fan; Zhang, Xiang

doi:10.1109/icdm.2016.0146

Cited by 7 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Usually, this kind tasks require fusion of different similarity representations of a network as different graphs (Serra, Greco & Tagliaferri, 2015;Xue et al, 2015), preserving graph structure (Hou et al, 2017) or simultaneously performing semi-supervised classification and clustering with adaptive kNN model (Nie, Cai & Li, 2017). Different domain network clustering was suggested in Cheng et al (2013) and improved in the following works suggesting fusion of different not-synchronized networks with different structures (Ni et al, 2016), cross-domain associations (Liu et al, 2015b) or multi-view spectral clustering (Li et al, 2015b). Khasahmadi et al (2020) propose a memory layer for graphs, that can efficiently learn graph hierarchical representations.…”

Section: Subgraph (And Graph) Embeddingmentioning

confidence: 99%

Survey on graph embeddings and their applications to machine learning problems on graphs

Makarov

Kiselev

Nikitinsky

et al. 2021

PeerJ Computer Science

View full text Add to dashboard Cite

Dealing with relational data always required significant computational resources, domain expertise and task-dependent feature engineering to incorporate structural information into a predictive model. Nowadays, a family of automated graph feature engineering techniques has been proposed in different streams of literature. So-called graph embeddings provide a powerful tool to construct vectorized feature spaces for graphs and their components, such as nodes, edges and subgraphs under preserving inner graph properties. Using the constructed feature spaces, many machine learning problems on graphs can be solved via standard frameworks suitable for vectorized feature representation. Our survey aims to describe the core concepts of graph embeddings and provide several taxonomies for their description. First, we start with the methodological approach and extract three types of graph embedding models based on matrix factorization, random-walks and deep learning approaches. Next, we describe how different types of networks impact the ability of models to incorporate structural and attributed data into a unified embedding. Going further, we perform a thorough evaluation of graph embedding applications to machine learning problems on graphs, among which are node classification, link prediction, clustering, visualization, compression, and a family of the whole graph embedding algorithms suitable for graph classification, similarity and alignment problems. Finally, we overview the existing applications of graph embeddings to computer science domains, formulate open problems and provide experiment results, explaining how different networks properties result in graph embeddings quality in the four classic machine learning problems on graphs, such as node classification, link prediction, clustering and graph visualization. As a result, our survey covers a new rapidly growing field of network feature engineering, presents an in-depth analysis of models based on network types, and overviews a wide range of applications to machine learning problems on graphs.

show abstract

Section: Subgraph (And Graph) Embeddingmentioning

confidence: 99%

Survey on graph embeddings and their applications to machine learning problems on graphs

Makarov

Kiselev

Nikitinsky

et al. 2021

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…Ever since Watts proposed the small world phenomenon, multi-mode and heterogeneous networks have been a subject of keen interest for network science researchers [1], [4], [5], [9], [10]. Algorithms for discovering social network communities represent a classic yet challenging problem [21] for this field of study.…”

Section: Introductionmentioning

confidence: 99%

Multi-Mode Social Network Clustering via Non-Negative Tri-Matrix Factorization With Cluster Indicator Similarity Regularization

Peng

2019

IEEE Access

View full text Add to dashboard Cite

Community discovery algorithms are important aspects of network science, especially as social network structures become more complex. Multi-mode social networks have recently become a challenging and popular topic in this field. At present, inner-mode relationship is mainly considered in community discovery algorithms for social networks. Thus, the effect of the these methods is not well in clustering as the intra-mode relationship is not considered in the clustering methods. In this paper, we propose a flexible and robust clustering framework, MRTA (the Multi-Similarity Regular Tri-Factorization Algorithm), based on non-negative tri-matrix factorization. MRTA has several advantages over the existing methods. First, it achieves more consistent clustering results based on cluster indicator of inner-mode and intra-mode relationships of multi-mode networks. Second, it can simultaneously cluster multiple modes, which is impossible for single-mode clustering algorithms. Finally, it provides a multi-mode clustering solution that is more robust to noise. We perform an efficient iterative update algorithm, and theoretically prove its accuracy. Extensive experimental results of a variety of real and synthetic networks demonstrate the effectiveness of our approach. INDEX TERMS Cluster indicator, multi-mode social network, non-negative tri-matrix factorization.

show abstract

“…To address the limitation of the existing methods, in this paper, we develop a more robust and flexible network model [22–24]. In this model, each disease is allowed to have its own tissue-specific molecular network.…”

Section: Introductionmentioning

confidence: 99%

Disease gene prioritization by integrating tissue-specific molecular networks using a robust multi-network model

Koyutürk

Tong

et al. 2016

BMC Bioinformatics

Self Cite

View full text Add to dashboard Cite

BackgroundAccurately prioritizing candidate disease genes is an important and challenging problem. Various network-based methods have been developed to predict potential disease genes by utilizing the disease similarity network and molecular networks such as protein interaction or gene co-expression networks. Although successful, a common limitation of the existing methods is that they assume all diseases share the same molecular network and a single generic molecular network is used to predict candidate genes for all diseases. However, different diseases tend to manifest in different tissues, and the molecular networks in different tissues are usually different. An ideal method should be able to incorporate tissue-specific molecular networks for different diseases.ResultsIn this paper, we develop a robust and flexible method to integrate tissue-specific molecular networks for disease gene prioritization. Our method allows each disease to have its own tissue-specific network(s). We formulate the problem of candidate gene prioritization as an optimization problem based on network propagation. When there are multiple tissue-specific networks available for a disease, our method can automatically infer the relative importance of each tissue-specific network. Thus it is robust to the noisy and incomplete network data. To solve the optimization problem, we develop fast algorithms which have linear time complexities in the number of nodes in the molecular networks. We also provide rigorous theoretical foundations for our algorithms in terms of their optimality and convergence properties. Extensive experimental results show that our method can significantly improve the accuracy of candidate gene prioritization compared with the state-of-the-art methods.ConclusionsIn our experiments, we compare our methods with 7 popular network-based disease gene prioritization algorithms on diseases from Online Mendelian Inheritance in Man (OMIM) database. The experimental results demonstrate that our methods recover true associations more accurately than other methods in terms of AUC values, and the performance differences are significant (with paired t-test p-values less than 0.05). This validates the importance to integrate tissue-specific molecular networks for studying disease gene prioritization and show the superiority of our network models and ranking algorithms toward this purpose. The source code and datasets are available at http://nijingchao.github.io/CRstar/.Electronic supplementary materialThe online version of this article (doi:10.1186/s12859-016-1317-x) contains supplementary material, which is available to authorized users.

show abstract

Self-Grouping Multi-network Clustering

Cited by 7 publications

References 13 publications

Survey on graph embeddings and their applications to machine learning problems on graphs

Survey on graph embeddings and their applications to machine learning problems on graphs

Multi-Mode Social Network Clustering via Non-Negative Tri-Matrix Factorization With Cluster Indicator Similarity Regularization

Disease gene prioritization by integrating tissue-specific molecular networks using a robust multi-network model

Contact Info

Product

Resources

About