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.
翻译:图形神经网络 (GNN) 已应用于各种图形任务 。 GNN的大多数现有工作都基于以下假设: 给定的图形数据是最佳的, 虽然在用于培训的图形数据中不可避免地存在缺失或不完整的边缘, 从而导致性能退化 。 在本文中, 我们提议以 GNN 为基础的同时学习图形结构和下游任务的GNN 联合学习框架“ 创造性预测网络 ” ( GPNN) 。 具体地说, 我们为这一联合学习任务开发了双级优化框架, 即上优化( 生成器) 和低优化( 优化器) 都与 GNN 同步。 根据我们的知识, 我们的方法是第一个基于 GNN 的双级优化框架 。 通过广泛的实验, 我们的方法超越了使用基准数据集建立的广泛基线 。