Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings
This work addresses the challenge of optimizing graph structures for better node embeddings in graph neural networks, which is incremental as it builds on existing graph learning methods by introducing an iterative and scalable approach.
The paper tackles the problem of jointly learning graph structure and node embeddings for graph neural networks, proposing an iterative framework (IDGL) that alternates between improving graph structure and embeddings, and a scalable version (IDGL-Anch) that reduces complexity without performance loss. The result is consistent outperformance or matching of state-of-the-art baselines on nine benchmarks, with improved robustness to adversarial graphs and support for both transductive and inductive learning.
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.