arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.05964cs.LG
收藏

GPN:一个用于图神经网络的联合结构学习框架

GPN: A Joint Structural Learning Framework for Graph Neural Networks

Tencent AI Lab(腾讯人工智能实验室)

Qianggang Ding, Deheng Ye, Tingyang Xu, Peilin Zhao

摘要:

图神经网络(GNN)已经被应用到各种图任务中。现有的GNN大多数工作都是基于给定的图数据是最优的假设,而在用于训练的图数据中不可避免地存在缺失或不完整的边,从而导致性能下降。在本文中,我们提出了生成预测网络(GPN),这是一种基于GNN的联合学习框架,可以同时学习图结构和下游任务。具体来说,我们为这个联合学习任务开发了一个双层优化框架,其中上层优化(生成器)和下层优化(预测器)都使用GNN实例化。据我们所知,我们的方法是第一个基于GNN的双层优化框架来解决这个任务。通过大量的实验,我们的方法优于使用基准数据集的各种基线。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑