Affentive graph-based recursive neural network for collective vertex classification

Date

2017

Authors

Xu, Qiongkai
Wang, Qing
Xu, Chenchen
Qu, Lizhen

Journal Title

Journal ISSN

Volume Title

Publisher

ACM

Abstract

Vertex classification is a critical task in graph analysis, where both contents and linkage of vertices are incorporated during classification. Recently, researchers proposed using deep neural network to build an end-to-end framework, which can capture both local content and structure information. These approaches were proved effective in incorporating semantic meanings of neighbouring vertices, while the usefulness of this information was not properly considered. In this paper, we propose an Attentive Graph-based Recursive Neural Network (AGRNN), which exerts attention on neural network to make our model focus on vertices with more relevant semantic information. We evaluated our approach on three real-world datasets and also datasets with synthetic noise. Our experimental results show that AGRNN achieves the state-of-the-art performance, in terms of effectiveness and robustness. We have also illustrated some attention weight samples to demonstrate the rationality of our model.

Description

Keywords

Recursive Neural Network, Collective Vertex Classification, Attention Model

Citation

Source

Proceedings of the 2017 ACM on Conference on Information and Knowledge Management

Type

Conference paper

Book Title

Entity type

Access Statement

License Rights

DOI

10.1145/3132847.3133081

Restricted until

2099-12-31