GPN: A Joint Structural Learning Framework for Graph Neural Networks
This addresses a common issue in graph-based machine learning for researchers and practitioners, but it is incremental as it builds on existing GNN methods.
The paper tackles the problem of missing or incomplete edges in graph data for training graph neural networks (GNNs), which degrades performance, by proposing GPN, a joint learning framework that simultaneously learns graph structure and downstream tasks, and it outperforms baselines on benchmark datasets.
Graph neural networks (GNNs) have been applied into a variety of graph tasks. Most existing work of GNNs is based on the assumption that the given graph data is optimal, while it is inevitable that there exists missing or incomplete edges in the graph data for training, leading to degraded performance. In this paper, we propose Generative Predictive Network (GPN), a GNN-based joint learning framework that simultaneously learns the graph structure and the downstream task. Specifically, we develop a bilevel optimization framework for this joint learning task, in which the upper optimization (generator) and the lower optimization (predictor) are both instantiated with GNNs. To the best of our knowledge, our method is the first GNN-based bilevel optimization framework for resolving this task. Through extensive experiments, our method outperforms a wide range of baselines using benchmark datasets.