Contrastive learning has emerged as a powerful tool for graph representation learning. However, most contrastive learning methods learn features of graphs with fixed coarse-grained scale, which might underestimate either local or global information. To capture more hierarchical and richer representation, we propose a novel Hierarchical Contrastive Learning (HCL) framework that explicitly learns graph representation in a hierarchical manner. Specifically, HCL includes two key components: a novel adaptive Learning to Pool (L2Pool) method to construct more reasonable multi-scale graph topology for more comprehensive contrastive objective, a novel multi-channel pseudo-siamese network to further enable more expressive learning of mutual information within each scale. Comprehensive experimental results show HCL achieves competitive performance on 12 datasets involving node classification, node clustering and graph classification. In addition, the visualization of learned representation reveals that HCL successfully captures meaningful characteristics of graphs.
翻译:对比性学习已成为图表代表性学习的有力工具。然而,大多数对比性学习方法都学习固定粗粗粗比例的图表特征,这些特征可能低估当地或全球信息。为了获取更分级和更富的代表性,我们提议一个新的等级和更富的代表性学习框架,以分级方式明确学习图表的表达方式。具体地说,高科技中心包括两个关键组成部分:一种新型适应性学习集合(L2pool)方法,为更全面的对比目标构建更合理的多尺度图形表层学,一种新型多通道伪西亚人网络,以进一步让更多表达了解每个尺度的相互信息。综合实验结果显示,高科技中心在涉及节点分类、节点组合和图形分类的12个数据集上取得了竞争性业绩。此外,对所学的代表性的可视化显示,高科技中心成功地捕捉了图的有意义的特征。