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

By Yu Chen, Lingfei Wu, Mohammed J. Zaki. Neural Information Processing Systems, 2020

532 citations recorded by the source corpus.

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 approaches close enough to the graph optimized for the 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 state-of-the-art baselines. Furthermore, IDGL can be more robust to adversarial graphs and cope with both transductive and inductive learning.

Subfields: Artificial Intelligence, Neurology

View Paper: https://www.semanticscholar.org/paper/ff6a4a9a41b78c8b1fcab185db780266bbb06caf

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yong Li
2. Yu Zheng
3. Liang Wang
4. Zenan Li
5. Wentao Zhao
6. Yanan Niu
7. Yiqun Hui
8. Yang Song

In Neurology

1. Liang Wang
2. Junchi Yan

Citations in the corpus

• NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification (2023, methodology): “02M IDGL [4] Function Fixed Required Yes O(N(2)) or O(Nm)† 0.”
• Multi-view Contrastive Graph Clustering (2021, unknown): “The reason of introducing graph learning is that the initial graph is often noisy or incomplete, which leads to suboptimal solutions [Chen et al., 2020b, Kang et al., 2020b].”
• Mining Latent Structures for Multimedia Recommendation (2021, methodology): “There are three categories of GSL methods: metric learning [5, 22, 37], probabilistic modeling [8, 25, 48], and direct optimization approaches [9, 17, 42].”
• Sequential Recommendation with Graph Neural Networks (2021, methodology): “To increase the expressive power and stabilize the learning process, the similarity metric function can be extended to the multihead metric [5, 25].”