Collective Vertex Classification Using Recursive Neural Network
This work addresses the problem of noisy neighbor features in graph classification for researchers in network analysis, but it is incremental as it adapts existing neural units to a graph context.
The paper tackles collective vertex classification in graphs by proposing a graph-based recursive neural network framework that uses both vertex attributes and neighboring vertex representations, achieving better results with a long short-term memory unit compared to baseline methods on four real-world datasets.
Collective classification of vertices is a task of assigning categories to each vertex in a graph based on both vertex attributes and link structure. Nevertheless, some existing approaches do not use the features of neighbouring vertices properly, due to the noise introduced by these features. In this paper, we propose a graph-based recursive neural network framework for collective vertex classification. In this framework, we generate hidden representations from both attributes of vertices and representations of neighbouring vertices via recursive neural networks. Under this framework, we explore two types of recursive neural units, naive recursive neural unit and long short-term memory unit. We have conducted experiments on four real-world network datasets. The experimental results show that our frame- work with long short-term memory model achieves better results and outperforms several competitive baseline methods.