Wang Yu, Hu Liang, Wu Yang, Gao Wanfu
College of Computer Science and Technology, Jilin University, Changchun 130012, China.
Entropy (Basel). 2022 Nov 29;24(12):1745. doi: 10.3390/e24121745.
Graph neural networks (GNNs), which work with graph-structured data, have attracted considerable attention and achieved promising performance on graph-related tasks. While the majority of existing GNN methods focus on the convolutional operation for encoding the node representations, the graph pooling operation, which maps the set of nodes into a coarsened graph, is crucial for graph-level tasks. We argue that a well-defined graph pooling operation should avoid the information loss of the local node features and global graph structure. In this paper, we propose a hierarchical graph pooling method based on the multihead attention mechanism, namely GMAPS, which compresses both node features and graph structure into the coarsened graph. Specifically, a multihead attention mechanism is adopted to arrange nodes into a coarsened graph based on their features and structural dependencies between nodes. In addition, to enhance the expressiveness of the cluster representations, a self-supervised mechanism is introduced to maximize the mutual information between the cluster representations and the global representation of the hierarchical graph. Our experimental results show that the proposed GMAPS obtains significant and consistent performance improvements compared with state-of-the-art baselines on six benchmarks from the biological and social domains of graph classification and reconstruction tasks.
图神经网络（GNNs）用于处理图结构数据，在与图相关的任务上引起了广泛关注并取得了良好的性能。虽然大多数现有的GNN方法专注于用于编码节点表示的卷积操作，但将节点集映射到粗化图的图池化操作对于图级任务至关重要。我们认为，一个定义良好的图池化操作应避免局部节点特征和全局图结构的信息损失。在本文中，我们提出了一种基于多头注意力机制的分层图池化方法，即GMAPS，它将节点特征和图结构都压缩到粗化图中。具体来说，采用多头注意力机制根据节点的特征和节点之间的结构依赖关系将节点排列成粗化图。此外，为了增强聚类表示的表现力，引入了一种自监督机制，以最大化聚类表示与分层图的全局表示之间的互信息。我们的实验结果表明，在图分类和重建任务的生物和社会领域的六个基准上，与现有最先进的基线相比，所提出的GMAPS取得了显著且一致的性能提升。
