Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings

TL;DR

This paper introduces IDGL, an iterative framework that jointly learns graph structure and node embeddings, improving accuracy and robustness in graph neural network tasks through a scalable, adaptive approach.

Contribution

The paper presents a novel end-to-end iterative graph learning method that enhances node embeddings and graph structure simultaneously, with a scalable version for large graphs.

Findings

IDGL outperforms state-of-the-art methods on nine benchmarks.

IDGL demonstrates robustness against adversarial graph attacks.

The scalable IDGL-Anch maintains performance with reduced complexity.

Abstract

In this paper, we propose an end-to-end graph learning framework, namely Iterative Deep Graph Learning (IDGL), for jointly and iteratively learning graph structure and graph embedding. The key rationale of IDGL is to learn a better graph structure based on better node embeddings, and vice versa (i.e., better node embeddings based on a better graph structure). Our iterative method dynamically stops when the learned graph structure approaches close enough to the graph optimized for the downstream prediction task. In addition, we cast the graph learning problem as a similarity metric learning problem and leverage adaptive graph regularization for controlling the quality of the learned graph. Finally, combining the anchor-based approximation technique, we further propose a scalable version of IDGL, namely IDGL-Anch, which significantly reduces the time and space complexity of IDGL without compromising the performance. Our extensive experiments on nine benchmarks show that our proposed IDGL models can consistently outperform or match the state-of-the-art baselines. Furthermore, IDGL can be more robust to adversarial graphs and cope with both transductive and inductive learning.