CommPOOL: An Interpretable Graph Pooling Framework for Hierarchical Graph Representation Learning
CommPOOL: An Interpretable Graph Pooling Framework for Hierarchical Graph Representation Learning
复制标题
DOI：
10.1016/j.neunet.2021.07.028
复制
发表时间：
2020-12
期刊：
影响因子：
--
通讯作者：
Haoteng Tang;Guixiang Ma;Lifang He;Heng Huang;L. Zhan
中科院分区：
文献类型：
--
作者：
Haoteng Tang;Guixiang Ma;Lifang He;Heng Huang;L. Zhan
近年来，层次图池神经网络（HGPNN）的出现和蓬勃发展，这是有效的图表示学习方法的图级任务，如图分类。然而，当前的HGPNN没有充分利用图的固有结构（例如，社区结构）。此外，现有HGPNN中的池化操作难以解释。在本文中，我们提出了一个新的可解释的图池框架- CommPOOL，它可以捕获和保存图表示学习过程中的图的层次社区结构。具体而言，CommPOOL中提出的社区池机制利用无监督方法以可解释的方式捕获图的固有社区结构。CommPOOL是一个通用而灵活的分层图表示学习框架，可以进一步促进各种图级任务。在五个公共基准数据集和一个合成数据集上的评估表明，与最先进的基线方法相比，CommPOOL在图分类的图表示学习中具有上级性能，并且在捕获和保存图的社区结构方面具有有效性。
Recent years have witnessed the emergence and flourishing of hierarchical graph pooling neural networks (HGPNNs) which are effective graph representation learning approaches for graph level tasks such as graph classification. However, current HGPNNs do not take full advantage of the graph’s intrinsic structures (e.g., community structure). Moreover, the pooling operations in existing HGPNNs are difficult to be interpreted. In this paper, we propose a new interpretable graph pooling framework — CommPOOL, that can capture and preserve the hierarchical community structure of graphs in the graph representation learning process. Specifically, the proposed community pooling mechanism in CommPOOL utilizes an unsupervised approach for capturing the inherent community structure of graphs in an interpretable manner. CommPOOL is a general and flexible framework for hierarchical graph representation learning that can further facilitate various graph-level tasks. Evaluations on five public benchmark datasets and one synthetic dataset demonstrate the superior performance of CommPOOL in graph representation learning for graph classification compared to the state-of-the-art baseline methods, and its effectiveness in capturing and preserving the community structure of graphs.