A Self-supervised Mixed-curvature Graph Neural Network
A Self-supervised Mixed-curvature Graph Neural Network
复制标题
DOI：
10.1609/aaai.v36i4.20333
复制
发表时间：
2021-12
期刊：
影响因子：
--
通讯作者：
Li Sun;Zhongbao Zhang;Junda Ye;Hao Peng;Jiawei Zhang;Sen Su;Philip S. Yu
中科院分区：
文献类型：
--
作者：
Li Sun;Zhongbao Zhang;Junda Ye;Hao Peng;Jiawei Zhang;Sen Su;Philip S. Yu
图表示学习近年来受到越来越多的关注。现有的方法大多忽略了图结构的复杂性，将图限制在单一的常曲率表示空间中，只适用于特定类型的图结构。此外，这些方法遵循监督或半监督学习范式，因此在实际应用中明显限制了它们在未标记图上的部署。为了解决上述局限性，我们首次尝试研究混合曲率空间中的自监督图表示学习。本文提出了一种新的自监督混合曲率图神经网络（SelfMGNN）。为了捕获复杂的图结构，我们通过多个黎曼分量空间的笛卡尔积构造了一个混合曲率空间，并设计了分层注意机制来学习和融合这些分量空间中的图表示。为了实现自监督学习，我们提出了一种新的双重对比方法。构建的混合曲率空间实际上为对比学习提供了多个黎曼视图。我们引入了一个黎曼投影器来显示这些视图，并利用一个精心设计的黎曼鉴别器来进行黎曼视图内和跨视图的单视图和跨视图对比学习。最后，大量的实验表明，SelfMGNN捕获了复杂的图结构，并且优于最先进的基线。
Graph representation learning received increasing attentions in recent years. Most of the existing methods ignore the complexity of the graph structures and restrict graphs in a single constant-curvature representation space, which is only suitable to particular kinds of graph structure indeed. Additionally, these methods follow the supervised or semi-supervised learning paradigm, and thereby notably limit their deployment on the unlabeled graphs in real applications. To address these aforementioned limitations, we take the first attempt to study the self-supervised graph representation learning in the mixed-curvature spaces. In this paper, we present a novel Self-Supervised Mixed-Curvature Graph Neural Network (SelfMGNN). To capture the complex graph structures, we construct a mixed-curvature space via the Cartesian product of multiple Riemannian component spaces, and design hierarchical attention mechanisms for learning and fusing graph representations across these component spaces. To enable the self-supervised learning, we propose a novel dual contrastive approach. The constructed mixed-curvature space actually provides multiple Riemannian views for the contrastive learning. We introduce a Riemannian projector to reveal these views, and utilize a well-designed Riemannian discriminator for the single-view and cross-view contrastive learning within and across the Riemannian views. Finally, extensive experiments show that SelfMGNN captures the complex graph structures and outperforms state-of-the-art baselines.