# Node Attribute Generation on Graphs

## TL;DR

This paper introduces NANG, a deep adversarial learning method for generating missing node attributes in graphs, improving performance in tasks like node classification and graph data augmentation.

## Contribution

The paper proposes a novel neural generator that learns a shared latent space for node attributes and graph structures, enabling effective attribute generation across modalities.

## Key findings

- Generated node attributes are high-quality and beneficial for downstream tasks.
- The method outperforms existing approaches on four real-world datasets.
- Generated attributes improve node classification accuracy.

## Abstract

Graph structured data provide two-fold information: graph structures and node attributes. Numerous graph-based algorithms rely on both information to achieve success in supervised tasks, such as node classification and link prediction. However, node attributes could be missing or incomplete, which significantly deteriorates the performance. The task of node attribute generation aims to generate attributes for those nodes whose attributes are completely unobserved. This task benefits many real-world problems like profiling, node classification and graph data augmentation. To tackle this task, we propose a deep adversarial learning based method to generate node attributes; called node attribute neural generator (NANG). NANG learns a unifying latent representation which is shared by both node attributes and graph structures and can be translated to different modalities. We thus use this latent representation as a bridge to convert information from one modality to another. We further introduce practical applications to quantify the performance of node attribute generation. Extensive experiments are conducted on four real-world datasets and the empirical results show that node attributes generated by the proposed method are high-qualitative and beneficial to other applications. The datasets and codes are available online.