Home >

news Help

Publication Information


Title
Japanese:構造特徴とグラフ畳み込みを用いたネットワークの半教師あり学習 
English: 
Author
Japanese: 立花誠人, 村田剛志.  
English: Makoto Tachibana, Tsuyoshi MURATA.  
Language Japanese 
Journal/Book name
Japanese:人工知能学会研究会資料 
English: 
Volume, Number, Page SIG-KBS-B802        pp. 20-25
Published date Nov. 23, 2018 
Publisher
Japanese:人工知能学会 
English: 
Conference name
Japanese:第115回人工知能学会知識ベースシステム研究会 
English: 
Conference site
Japanese:神奈川 
English: 
Official URL https://jsai.ixsq.nii.ac.jp/ej/?action=pages_view_main&active_action=repository_view_main_item_detail&item_id=9541&item_no=1&page_id=13&block_id=23
 
Abstract Since several types of data can be represented as graphs, there has been a demand for generalizing neural network models for graph data. Graph convolution is a recent scalable method for performing deep feature learning on attributed graphs by aggregating local node information over multiple layers. Such layers only consider attribute information of node neighbors in the forward model and do not incorporate knowledge of global network structure in the learning task. In this paper, we present a scalable semi-supervised learning method for graph-structured data which considers not only neighbors information, but also the global network structure. In our method, we add a term preserving the network structural features such as centrality to the objective function of Graph Convolutional Network and train for both node classification and network structure preservation simultaneously. Experimental results showed that our method outperforms state-of-the-art baselines for the node classification tasks in the sparse label regime.
Award 人工知能学会研究会優秀賞

©2007 Tokyo Institute of Technology All rights reserved.