Graph pooling methods have been widely used on downsampling graphs, achieving impressive results on multiple graph-level tasks like graph classification and graph generation. An important line called node dropping pooling aims at exploiting learnable scoring functions to drop nodes with comparatively lower significance scores. However, existing node dropping methods suffer from two limitations: (1) for each pooled node, these models struggle to capture long-range dependencies since they mainly take GNNs as the backbones; (2) pooling only the highest-scoring nodes tends to preserve similar nodes, thus discarding the affluent information of low-scoring nodes. To address these issues, we propose a Graph Transformer Pooling method termed GTPool, which introduces Transformer to node dropping pooling to efficiently capture long-range pairwise interactions and meanwhile sample nodes diversely. Specifically, we design a scoring module based on the self-attention mechanism that takes both global context and local context into consideration, measuring the importance of nodes more comprehensively. GTPool further utilizes a diversified sampling method named Roulette Wheel Sampling (RWS) that is able to flexibly preserve nodes across different scoring intervals instead of only higher scoring nodes. In this way, GTPool could effectively obtain long-range information and select more representative nodes. Extensive experiments on 11 benchmark datasets demonstrate the superiority of GTPool over existing popular graph pooling methods.

翻译：图池化方法已广泛应用于图的下采样过程，在图分类和图生成等多项图级别任务中取得了显著成果。其中，节点丢弃池化这一重要分支旨在利用可学习的评分函数丢弃重要性分数较低的节点。然而，现有节点丢弃方法存在两个局限：（1）对于每个被池化的节点，这些模型难以捕获长距离依赖关系，因为它们主要采用图神经网络作为主干网络；（2）仅保留得分最高的节点倾向于保留相似的节点，从而丢弃了低分节点的丰富信息。为解决这些问题，我们提出一种名为GTPool的图Transformer池化方法，该方法将Transformer引入节点丢弃池化，以高效捕获长距离成对交互作用，同时实现节点的多样化采样。具体而言，我们设计了一种基于自注意力机制的评分模块，该模块同时考虑全局上下文和局部上下文，更全面地衡量节点的重要性。GTPool进一步采用名为轮盘赌采样（RWS）的多样化采样方法，能够灵活地保留不同评分区间内的节点，而不仅仅是高分节点。通过这种方式，GTPool可有效获取长距离信息并选择更具代表性的节点。在11个基准数据集上的大量实验表明，GTPool在性能上优于现有主流图池化方法。