Graph Convolutional Networks (GCNs), similarly to Convolutional Neural Networks (CNNs), are typically based on two main operations - spatial and point-wise convolutions. In the context of GCNs, differently from CNNs, a pre-determined spatial operator based on the graph Laplacian is often chosen, allowing only the point-wise operations to be learnt. However, learning a meaningful spatial operator is critical for developing more expressive GCNs for improved performance. In this paper we propose pathGCN, a novel approach to learn the spatial operator from random paths on the graph. We analyze the convergence of our method and its difference from existing GCNs. Furthermore, we discuss several options of combining our learnt spatial operator with point-wise convolutions. Our extensive experiments on numerous datasets suggest that by properly learning both the spatial and point-wise convolutions, phenomena like over-smoothing can be inherently avoided, and new state-of-the-art performance is achieved.
翻译:与进化神经网络(CNNs)相似,进化网络(GCNs)通常以两种主要操作为基础:空间和点进化。在GCNs方面,不同于CNNs,通常选择一个以Laplacecian图为基础的预先确定的空间操作员,只允许进行点学操作。然而,学习一个有意义的空间操作员对于开发更显眼的GCN对于提高性能至关重要。在本文中,我们建议了路径GCN,这是一种从图上随机路径中学习空间操作员的新办法。我们分析了我们方法的趋同及其与现有GCNs的差异。此外,我们讨论了将我们所学的空间操作员与点进化共进化相结合的几种选择。我们在众多数据集上进行的广泛实验表明,通过正确学习空间和点进化的演进,可以自然避免过度抽动等现象,并实现新的状态性能。