2,189 Hits in 1.5 sec

Graph Regularized Transductive Classification on Heterogeneous Information Networks [chapter]

Ming Ji, Yizhou Sun, Marina Danilevsky, Jiawei Han, Jing Gao
2010 Lecture Notes in Computer Science  
In this paper, we consider the transductive classification problem on heterogeneous networked data which share a common topic.  ...  However, although classification on homogeneous networks has been studied for decades, classification on heterogeneous networks has not been explored until recently.  ...  Transductive classification on heterogeneous information networks.  ... 
doi:10.1007/978-3-642-15880-3_42 fatcat:r47krvy7tbgkvdponhgzcdh2za

Graph Regularized Meta-path Based Transductive Regression in Heterogeneous Information Network [chapter]

Mengting Wan, Yunbo Ouyang, Lance Kaplan, Jiawei Han
2015 Proceedings of the 2015 SIAM International Conference on Data Mining  
In this paper, we consider a graph regularized meta-path based transductive regression model (Grempt), which combines the principal philosophies of typical graph-based transductive classification methods  ...  A number of real-world networks are heterogeneous information networks, which are composed of different types of nodes and links.  ...  For heterogeneous networks, some graph-based classification models [1] [2] [3] have been proposed.  ... 
doi:10.1137/1.9781611974010.103 pmid:26705510 pmcid:PMC4688014 dblp:conf/sdm/WanOKH15 fatcat:s7u6do2x4rdivivmprstaelani

Mining heterogeneous information networks

Jaiwei Han
2012 Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '12  
., "Graph Regularized Transductive Classification on Heterogeneous Information Networks", ECMLPKDD'10. M. Ji, M.  ...  ., "Graph Regularized Transductive Classification on Heterogeneous Information Networks", ECMLPKDD'10 23 ( ) ( ) 1 ( ) ( ) 2 , , 1 1 1 , , ( ) ( ) ( ) ( ) 1 ( ,..., ) 1 1  ...   Much more to be explored in information network mining!  ... 
doi:10.1145/2339530.2339533 dblp:conf/kdd/Han12 fatcat:2kycyso37fgu5f5a2tai52bhem

Graph Representation Learning Network via Adaptive Sampling [article]

Anderson de Andrade, Chen Liu
2020 arXiv   pre-print
Graph Attention Network (GAT) and GraphSAGE are neural network architectures that operate on graph-structured data and have been widely studied for link prediction and node classification.  ...  We conduct experiments on both transductive and inductive settings.  ...  We use an attention mechanism similar to the one in Graph Attention Networks (GAT) [28] .  ... 
arXiv:2006.04637v1 fatcat:zvri6b65kffxtcwhnhqfiwitre

Meta-path Free Semi-supervised Learning for Heterogeneous Networks [article]

Shin-woo Park, Byung Jun Bae, Jinyoung Yeo, Seung-won Hwang
2021 arXiv   pre-print
Graph neural networks (GNNs) have been widely used in representation learning on graphs and achieved superior performance in tasks such as node classification.  ...  However, analyzing heterogeneous graph of different types of nodes and links still brings great challenges for injecting the heterogeneity into a graph neural network.  ...  To extremely ablate the effect of heterogeneity relaxation, we also perform the node classification task with no heterogeneity on graphs.  ... 
arXiv:2010.08924v2 fatcat:7dkluz7eyrcjfj37f6roshu24y

Robust Classification of Information Networks by Consistent Graph Learning [chapter]

Shi Zhi, Jiawei Han, Quanquan Gu
2015 Lecture Notes in Computer Science  
These inconsistent links raise a big challenge for graph regularization and deteriorate the classification performance significantly.  ...  Graph regularization-based methods have achieved great success for network classification by making the label-link consistency assumption, i.e., if two nodes are linked together, they are likely to belong  ...  In this case, graph regularization would fail. This shows the drawback of standard graph regularization technique for network classification.  ... 
doi:10.1007/978-3-319-23525-7_46 pmid:26705541 pmcid:PMC4688020 fatcat:iom6am3s5nekdmy3nveaaavuba

Learning latent representations of nodes for classifying in heterogeneous social networks

Yann Jacob, Ludovic Denoyer, Patrick Gallinari
2014 Proceedings of the 7th ACM international conference on Web search and data mining - WSDM '14  
While learning and performing inference on homogeneous networks have motivated a large amount of research, few work exists on heterogeneous networks and there are open and challenging issues for existing  ...  We address here the specific problem of nodes classification and tagging in heterogeneous social networks, where different types of nodes are considered, each type with its own label or tag set.  ...  The proposed algorithm operates in the transductive setting and makes use of a regularization framework.  ... 
doi:10.1145/2556195.2556225 dblp:conf/wsdm/JacobDG14 fatcat:klpzid4d5nferl35fpk5wobkxe

Music Classification By Transductive Learning Using Bipartite Heterogeneous Networks

Diego Furtado Silva, Rafael Geraldeli Rossi, Solange Oliveira Rezende, Gustavo Enrique De Almeida Prado Alves Batista
2014 Zenodo  
Transductive Classification Using Bipartite Heterogeneous Networks The main algorithms for transductive classification in data represented as networks are based on regularization [19] , which have to  ...  In this paper we used three regularization-based algorithms: (i) Tag-based classification Model (TM) [16] , (ii) Label Propagation based on Bipartite Heterogeneous Networks (LPBHN) [10] , and (iii) GNetMine  ... 
doi:10.5281/zenodo.1418264 fatcat:ic7iwvnaeva6nke6ekvhq4djfy

Single Network Relational Transductive Learning

A. Dhurandhar, J. Wang
2013 The Journal of Artificial Intelligence Research  
Relational classification on a single connected network has been of particular interest in the machine learning and data mining communities in the last decade or so.  ...  We further portray the efficacy of our approach on synthetic as well as real data, by comparing it with state-of-the-art relational learning algorithms, and graph transduction techniques with an adjacency  ...  In this paper, we provide a lucid way to effectively leverage a rich class of graph transduction methods, namely those based on the graph laplacian regularization framework, for within network relational  ... 
doi:10.1613/jair.4068 fatcat:fkdib57whvcgzis6ltbf2e7iyi

Lovasz Convolutional Networks [article]

Prateek Yadav, Madhav Nimishakavi, Naganand Yadati, Shikhar Vashishth, Arun Rajkumar, Partha Talukdar
2019 arXiv   pre-print
Semi-supervised learning on graph structured data has received significant attention with the recent introduction of Graph Convolution Networks (GCN).  ...  While traditional methods have focused on optimizing a loss augmented with Laplacian regularization framework, GCNs perform an implicit Laplacian type regularization to capture local graph structure.  ...  A common approach is to pose the classification problem as a semi-supervised graph transduction problem where one wishes to label all the nodes of a graph using the labels of a small subset of nodes.  ... 
arXiv:1805.11365v3 fatcat:i3zjynz6b5ffpelcrbz6uwdq3y

Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning [article]

Tong Chen, Hongzhi Yin, Jie Ren, Zi Huang, Xiangliang Zhang, Hao Wang
2021 arXiv   pre-print
Experiments on three real-world heterogeneous graphs have further validated the efficacy of WIDEN on both transductive and inductive node representation learning, as well as the superior training efficiency  ...  Recently, bearing the message passing paradigm, graph neural networks (GNNs) have greatly advanced the performance of node representation learning on graphs.  ...  transductive node classification.  ... 
arXiv:2104.01711v2 fatcat:uozthcnesjbszdf2ciauvvgrai

HeteGCN: Heterogeneous Graph Convolutional Networks for Text Classification [article]

Rahul Ragesh, Sundararajan Sellamanickam, Arun Iyer, Ram Bairi, Vijay Lingam
2020 arXiv   pre-print
We consider the problem of learning efficient and inductive graph convolutional networks for text classification with a large number of examples and features.  ...  To address these limitations, we propose a heterogeneous graph convolutional network (HeteGCN) modeling approach that unites the best aspects of PTE and TextGCN together.  ...  Like PTE , TextGCN [36] uses a heterogeneous graph but learns a text classifier model with a graph convolutional network and it outperforms many popular neural network models [12, 17] and PTE on several  ... 
arXiv:2008.12842v1 fatcat:bjt4dxun6zaltaloynz7ydxzn4

HinDom: A Robust Malicious Domain Detection System based on Heterogeneous Information Network with Transductive Classification [article]

Xiaoqing Sun, Mingkai Tong, Jiahai Yang
2019 arXiv   pre-print
Instead of relying on manually selected features, HinDom models the DNS scene as a Heterogeneous Information Network (HIN) consist of clients, domains, IP addresses and their diverse relationships.  ...  Besides, the metapath-based transductive classification method enables HinDom to detect malicious domains with only a small fraction of labeled samples.  ...  Acknowledgment We thank Hui Zhang, Chenxi Li, Shize Zhang for constructive recommendations on experiments and data processing.  ... 
arXiv:1909.01590v1 fatcat:2zphegvq6bgf5ktrzqdylb3kwm

Towards Shape-based Knee Osteoarthritis Classification using Graph Convolutional Networks [article]

Christoph von Tycowicz
2019 arXiv   pre-print
We formulate the grading task as semi-supervised node classification problem on a graph embedded in shape space.  ...  We present a transductive learning approach for morphometric osteophyte grading based on geometric deep learning.  ...  Employing graph convolutional filters, we are able to avoid explicit graph-based regularization by encoding the graph structure directly via a graph convolutional neural network model and training it on  ... 
arXiv:1910.06119v1 fatcat:yta3253nknfqtmhh66jtjppacq

Be More with Less: Hypergraph Attention Networks for Inductive Text Classification [article]

Kaize Ding, Jianling Wang, Jundong Li, Dingcheng Li, Huan Liu
2020 arXiv   pre-print
Recently, graph neural networks (GNNs) have received increasing attention in the research community and demonstrated their promising results on this canonical task.  ...  Extensive experiments on various benchmark datasets demonstrate the efficacy of the proposed approach on the text classification task.  ...  to illustrate the superiority of HyperGAT over other state-of-the-art methods on the text classification task. 2 Related Work Graph Neural Networks Graph neural networks (GNNs) -a family of neural models  ... 
arXiv:2011.00387v1 fatcat:jvvct7zx4vb6xbwnwljn3trvlq
« Previous Showing results 1 — 15 out of 2,189 results