Adaptive Kernel Graph Neural Network-猫眼课题宝

DOI：

10.1609/aaai.v36i6.20664

发表时间：

2021-12

期刊：

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Mingxuan Ju;Shifu Hou;Yujie Fan;Jianan Zhao;Liang Zhao;Yanfang Ye

图神经网络（gnn）在图结构数据的表示学习方面取得了巨大的成功。gnn中的分层图卷积在捕获图拓扑方面显示出强大的功能。在此过程中，gnn通常由预定义的核（如拉普拉斯矩阵、邻接矩阵或其变体）来引导。然而，采用预定义的核可能会限制对不同图的通用性：图和核之间的不匹配将导致次优性能。例如，当高频信息对图很重要时，关注低频信息的gnn可能无法获得令人满意的性能，反之亦然。为了解决这一问题，本文提出了一种新的框架，即自适应核图神经网络（AKGNN），它在第一次尝试中以统一的方式学习适应最优的图核。在提出的AKGNN中，我们首先设计了一个数据驱动的图核学习机制，该机制通过修改图拉普拉斯算子的最大特征值来自适应调节全通和低通滤波器之间的平衡。通过这一过程，AKGNN学习到高低频信号之间的最优阈值，解决了通用性问题。随后，我们通过参数化技巧进一步减少了参数的数量，并通过全局读出函数增强了表达能力。在公认的基准数据集上进行了大量的实验，结果表明，与最先进的gnn相比，我们提出的AKGNN具有出色的性能。源代码可以在：https://github.com/jumxglhf/AKGNN上公开获得。

Graph neural networks (GNNs) have demonstrated great success in representation learning for graph-structured data. The layer-wise graph convolution in GNNs is shown to be powerful at capturing graph topology. During this process, GNNs are usually guided by pre-defined kernels such as Laplacian matrix, adjacency matrix, or their variants. However, the adoptions of pre-defined kernels may restrain the generalities to different graphs: mismatch between graph and kernel would entail sub-optimal performance. For example, GNNs that focus on low-frequency information may not achieve satisfactory performance when high-frequency information is significant for the graphs, and vice versa. To solve this problem, in this paper, we propose a novel framework - i.e., namely Adaptive Kernel Graph Neural Network (AKGNN) - which learns to adapt to the optimal graph kernel in a unified manner at the first attempt. In the proposed AKGNN, we first design a data-driven graph kernel learning mechanism, which adaptively modulates the balance between all-pass and low-pass filters by modifying the maximal eigenvalue of the graph Laplacian. Through this process, AKGNN learns the optimal threshold between high and low frequency signals to relieve the generality problem. Later, we further reduce the number of parameters by a parameterization trick and enhance the expressive power by a global readout function. Extensive experiments are conducted on acknowledged benchmark datasets and promising results demonstrate the outstanding performance of our proposed AKGNN by comparison with state-of-the-art GNNs. The source code is publicly available at: https://github.com/jumxglhf/AKGNN.

Adaptive Kernel Graph Neural Network

文献摘要

相似文献