ANAE: Learning Node Context Representation for Attributed Network Embedding

TL;DR

ANAE introduces a novel auto-encoder framework that learns node context representations by modeling local subgraphs, effectively capturing both network structure and node attributes for improved attributed network embedding.

Contribution

The paper proposes a new auto-encoder approach that models local subgraphs to learn node context representations, addressing limitations of existing methods.

Findings

Outperforms state-of-the-art methods in link prediction

Achieves higher accuracy in node classification

Effectively captures both structure and attribute information

Abstract

Attributed network embedding aims to learn low-dimensional node representations from both network structure and node attributes. Existing methods can be categorized into two groups: (1) the first group learns two separated node representations from network structure and node attribute respectively and concatenates them together; (2) the other group obtains node representations by translating node attributes into network structure or vice versa. However, both groups have their drawbacks. The first group neglects the correlation between network structure and node attributes, while the second group assumes strong dependence between these two types of information. In this paper, we address attributed network embedding from a novel perspective, i.e., learning node context representation for each node via modeling its attributed local subgraph. To achieve this goal, we propose a novel attributed network auto-encoder framework, namely ANAE. For a target node, ANAE first aggregates the attribute information from its attributed local subgraph, obtaining its low-dimensional representation. Next, ANAE diffuses the representation of the target node to nodes in its local subgraph to reconstruct their attributes. Such an encoder-decoder framework allows the learned representations to better preserve the context information manifested in both network structure and node attributes, thus having high capacity to learn good node representations for attributed network. Extensive experimental results on real-world datasets demonstrate that the proposed framework outperforms the state-of-the-art approaches at the tasks of link prediction and node classification.