Author name cluster

Yingkui Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers

1 author row

AAAI Conference 2019 Conference Paper

Community Detection in Social Networks Considering Topic Correlations

Yingkui Wang
Di Jin
Katarzyna Musial
Jianwu Dang

Network contents including node contents and edge contents can be utilized for community detection in social networks. Thus, the topic of each community can be extracted as its semantic information. A plethora of models integrating topic model and network topologies have been proposed. However, a key problem has not been resolved that is the semantic division of a community. Since the definition of community is based on topology, a community might involve several topics. To achieve better community detection results and to better understand the fundamental community semantics, we investigate the correlations of different topics in community detection model. This work models the formation of each edge assuming that users are more likely to communicate with each other when they are in the same community and their topics are closely correlated. A Topic Correlations based Community Detection (TCCD) model is proposed, which can learn community structure and semantic interpretation of each community. Our model is evaluated on two real datasets and is compared with four state-of-the-art methods. Experimental results show that TCCD significantly improves the accuracy of community detection. Finally, a case study shows that TCCD can detect the topic correlations inside a community. And we can infer better semantic interpretation of each community.

PDF Details

IJCAI Conference 2019 Conference Paper

Masked Graph Convolutional Network

Liang Yang
Fan Wu
Yingkui Wang
Junhua Gu
Yuanfang Guo

Semi-supervised classification is a fundamental technology to process the structured and unstructured data in machine learning field. The traditional attribute-graph based semi-supervised classification methods propagate labels over the graph which is usually constructed from the data features, while the graph convolutional neural networks smooth the node attributes, i. e. , propagate the attributes, over the real graph topology. In this paper, they are interpreted from the perspective of propagation, and accordingly categorized into symmetric and asymmetric propagation based methods. From the perspective of propagation, both the traditional and network based methods are propagating certain objects over the graph. However, different from the label propagation, the intuition ``the connected data samples tend to be similar in terms of the attributes", in attribute propagation is only partially valid. Therefore, a masked graph convolution network (Masked GCN) is proposed by only propagating a certain portion of the attributes to the neighbours according to a masking indicator, which is learned for each node by jointly considering the attribute distributions in local neighbourhoods and the impact on the classification results. Extensive experiments on transductive and inductive node classification tasks have demonstrated the superiority of the proposed method.

PDF Details