CoANE: Modeling Context Co-occurrence for Attributed Network Embedding

TL;DR

CoANE introduces a novel attributed network embedding method that models context co-occurrence and social circles, effectively capturing structural and attribute information for improved link prediction, classification, and clustering.

Contribution

The paper proposes CoANE, a new ANE model that encodes context co-occurrence and social circles using convolutional mechanisms and a three-way objective function.

Findings

Outperforms state-of-the-art ANE models on five datasets

Improves link prediction, node classification, and clustering accuracy

Effectively captures social circles and attribute patterns

Abstract

Attributed network embedding (ANE) is to learn low-dimensional vectors so that not only the network structure but also node attributes can be preserved in the embedding space. Existing ANE models do not consider the specific combination between graph structure and attributes. While each node has its structural characteristics, such as highly-interconnected neighbors along with their certain patterns of attribute distribution, each node's neighborhood should be not only depicted by multi-hop nodes, but consider certain clusters or social circles. To model such information, in this paper, we propose a novel ANE model, Context Co-occurrence-aware Attributed Network Embedding (CoANE). The basic idea of CoANE is to model the context attributes that each node's involved diverse patterns, and apply the convolutional mechanism to encode positional information by treating each attribute as a channel. The learning of context co-occurrence can capture the latent social circles of each node. To better encode structural and semantic knowledge of nodes, we devise a three-way objective function, consisting of positive graph likelihood, contextual negative sampling, and attribute reconstruction. We conduct experiments on five real datasets in the tasks of link prediction, node label classification, and node clustering. The results exhibit that CoANE can significantly outperform state-of-the-art ANE models.