GPN: A Joint Structural Learning Framework for Graph Neural Networks

TL;DR

This paper introduces GPN, a novel GNN framework that jointly learns graph structure and performs tasks, addressing missing edges and improving performance through a bilevel optimization approach.

Contribution

It presents the first GNN-based bilevel optimization framework for joint graph structure learning and task prediction, enhancing robustness to incomplete data.

Findings

Outperforms baseline methods on benchmark datasets.

Effective in handling missing or incomplete graph edges.

Demonstrates significant performance improvements.

Abstract

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.