Proceedings Abstracts of the Twenty-Fifth International Joint Conference on Artificial Intelligence

Max-Margin DeepWalk: Discriminative Learning of Network Representation / 3889
Cunchao Tu, Weicheng Zhang, Zhiyuan Liu, Maosong Sun

DeepWalk is a typical representation learning method that learns low-dimensional representations for vertices in social networks. Similar to other network representation learning (NRL) models, it encodes the network structure into vertex representations and is learnt in unsupervised form. However, the learnt representations usually lack the ability of discrimination when applied to machine learning tasks, such as vertex classification. In this paper, we overcome this challenge by proposing a novel semi-supervised model, max-margin DeepWalk (MMDW). MMDW is a unified NRL framework that jointly optimizes the max-margin classifier and the aimed social representation learning model. Influenced by the max-margin classifier, the learnt representations not only contain the network structure, but also have the characteristic of discrimination. The visualizations of learnt representations indicate that our model is more discriminative than unsupervised ones, and the experimental results on vertex classification demonstrate that our method achieves a significant improvement than other state-of-the-art methods.