We introduce the gat2vec framework that uses structural information to generate structural contexts, attributes to generate attribute contexts, and employs a shallow neural network model to learn a joint representation from them. In this paper, we investigate how attributes can be modeled, and subsequently used along with structural information in learning the representation.
The learning methods should thus preserve both the structural and attribute aspects. When multiple sources of information are available, using a combination of them may be beneficial as they complement each other in generating accurate contexts moreover, their combined use may be fundamental when the information sources are sparse. Most NRL methods have focused just on structural information, and separately apply a traditional representation learning on attributes. Apart from their graph structure, networks are often associated with diverse information in the form of attributes. Network representation learning (NRL) enables the application of machine learning tasks such as classification, prediction and recommendation to networks. The experimental results on three real attributed networks show that the accuracy of node classification outperforms the state-of-the-art methods on the basis of our proposed network representation learning method. It uses the attribute random walk to take care of the node’s attribute information, and combines two random walk sequences to learn the network representation of the node using the skip-gram model. This method considers the structure and homogeneity of the network through a biased random walk. Based on the above, we propose a robust NRL method called Attributed Network Representation Learning Based on Biased Random Walk (ANRLBRW).
Combining attribute information can reconstruct the network better. In reality, the network contains a lot of attribute information, which brings opportunities and challenges to random walk. Random walk has a wide range of applications in structure-based network representation learning. Network representation learning(NRL) aims to learn the low-dimensional and continuous vector representations for all nodes in networks, which is used as the input feature for many complex networks analysis tasks.