AUTHOR=Wang Shanfeng , Wang Qixiang , Gong Maoguo 

TITLE=Multi-Task Learning Based Network Embedding

JOURNAL=Frontiers in Neuroscience

VOLUME=Volume 13 - 2019

YEAR=2020

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2019.01387

DOI=10.3389/fnins.2019.01387

ISSN=1662-453X

ABSTRACT=The goal of network representation learning, also called network embedding, is to encode the network structure information into a continuous low dimensionality embedding space, where geometric relationships among the vectors can reflect the relationships of nodes in original network. The existing network representation learning methods are always single task learning in which case these methods focus on preserving the proximity of nodes from one aspect. However, the proximity of nodes is dependent on both the local and global structure, resulting in a limitation on node embeddings learned by those methods. In order to solve the problem, in this paper we propose a novel method Multi-task Learning Based Network Embedding, namely MLNE. There are two tasks in this method so as to preserve the proximity of nodes. The aim of first task is to preserve the high order proximity between pairwise nodes in a whole network. The second task is to preserve the low order proximity in nodes' one-hop area. By jointly learning these tasks in the supervised deep learning model, our method can obtain node embeddings, which can sufficiently reflect the roles that nodes play in networks. In order to demonstrate the efficacy of our method MLNE over existing state-of-the-art methods, we conduct the experiments on multi-label classification, link prediction and visualization in four real-world networks. The experimental results show that our method has a competitive performance.