Community Aware Random Walk for Network Embedding
share
Social network analysis provides meaningful information about behavior of network members that can be used in diverse applications such as classification, link prediction, etc. however, network analysis is computationally expensive because of feature learning for different applications. In recent years, many researches have focused on feature learning methods in social networks. Network embedding represents the network in a lower dimensional representation space with the same properties which presents a compressed representation of the input network. In this paper, we introduce a novel algorithm named "CARE" for network embedding that can be used for different types of networks including weighted, directed and complex. While current methods try to preserve local neighborhood information of nodes, we utilize local neighborhood and community information of network nodes to cover both local and global structure of social networks. CARE builds customized paths, which are consisted of local and global structure of network nodes, as a basis for network embedding and uses skip-gram model to learn representation vector of nodes. Then, stochastic gradient descent is used to optimize our objective function and learn the final representation of nodes. Our method can be scalable when new nodes are appended to network without information loss. Parallelize generation of customized random walks is also used for speeding up CARE. We evaluate the performance of CARE on multi label classification and link prediction tasks. Experimental results on different networks indicate that the proposed method outperforms others in both Micro-f1 and Macro-f1 measures for different size of training data.
READ FULL TEXT
