论文标题
隐式图神经网络
Implicit Graph Neural Networks
论文作者
论文摘要
图形神经网络（GNN）是广泛使用的深度学习模型，可从图形结构数据中学习有意义的表示。由于基础复发结构的有限性质，当前的GNN方法可能难以捕获基础图中的远程依赖性。为了克服这一难度，我们提出了一个称为隐式图神经网络（IGNN）的图形学习框架，其中预测基于涉及隐式定义的“状态”向量的定点平衡方程的解决方案。我们使用Perron-Frobenius理论来得出足够的条件，以确保框架的适当性。利用隐式差异化，我们得出了一种可拖动的投影梯度下降方法来训练框架。在全面的任务上进行的实验表明，IGNN始终捕获长期依赖性并胜过最先进的GNN模型。
Graph Neural Networks (GNNs) are widely used deep learning models that learn meaningful representations from graph-structured data. Due to the finite nature of the underlying recurrent structure, current GNN methods may struggle to capture long-range dependencies in underlying graphs. To overcome this difficulty, we propose a graph learning framework, called Implicit Graph Neural Networks (IGNN), where predictions are based on the solution of a fixed-point equilibrium equation involving implicitly defined "state" vectors. We use the Perron-Frobenius theory to derive sufficient conditions that ensure well-posedness of the framework. Leveraging implicit differentiation, we derive a tractable projected gradient descent method to train the framework. Experiments on a comprehensive range of tasks show that IGNNs consistently capture long-range dependencies and outperform the state-of-the-art GNN models.
