Interpretable Node Representation with Attribute Decoding

TL;DR

This paper introduces NORAD, a novel interpretable model for node representation learning in graphs that emphasizes attribute decoding to capture community structures and improve isolated node representations.

Contribution

The paper proposes NORAD, a new model that enhances interpretability of node representations by integrating attribute decoding and community structure insights.

Findings

NORAD outperforms existing models in interpretability.

The rectifying procedure improves isolated node representations.

Empirical results validate the effectiveness of NORAD.

Abstract

Variational Graph Autoencoders (VGAEs) are powerful models for unsupervised learning of node representations from graph data. In this work, we systematically analyze modeling node attributes in VGAEs and show that attribute decoding is important for node representation learning. We further propose a new learning model, interpretable NOde Representation with Attribute Decoding (NORAD). The model encodes node representations in an interpretable approach: node representations capture community structures in the graph and the relationship between communities and node attributes. We further propose a rectifying procedure to refine node representations of isolated notes, improving the quality of these nodes' representations. Our empirical results demonstrate the advantage of the proposed model when learning graph data in an interpretable approach.