Heterogeneous Graph Structure Learning for Graph Neural Networks
Heterogeneous Graph Structure Learning for Graph Neural Networks
复制标题
DOI：
10.1609/aaai.v35i5.16600
复制
发表时间：
2021-05
期刊：
影响因子：
--
通讯作者：
Jianan Zhao;Xiao Wang;C. Shi;Binbin Hu;Guojie Song;Yanfang Ye
中科院分区：
文献类型：
--
作者：
Jianan Zhao;Xiao Wang;C. Shi;Binbin Hu;Guojie Song;Yanfang Ye
近年来，异构图神经网络（hgnn）越来越受到人们的关注，并在许多任务中取得了优异的成绩。现有hgnn的成功依赖于一个基本假设，即原始异构图结构是可靠的。然而，这种假设通常是不现实的，因为现实中的异构图不可避免地存在噪声或不完整。因此，学习hgnn的异构图结构而不是仅仅依赖于原始图结构是至关重要的。鉴于此，我们首次尝试为hgnn学习最优的异构图结构，并提出了一种新的框架HGSL，该框架将异构图结构学习和GNN参数学习共同用于分类任务。与传统同质图上的GSL不同，HGSL考虑到异构图中不同关系的异质性，独立生成每个关系子图。具体来说，在每个生成的关系子图中，HGSL不仅通过生成特征相似图来考虑特征的相似性，还通过生成特征传播图和语义图来考虑特征和语义之间复杂的异构交互。然后，将这些图融合到一个学习到的异构图中，并结合GNN对分类目标进行优化。在真实世界的图形上进行的大量实验表明，所提出的框架明显优于最先进的方法。
Heterogeneous Graph Neural Networks (HGNNs) have drawn increasing attention in recent years and achieved outstanding performance in many tasks. The success of the existing HGNNs relies on one fundamental assumption, i.e., the original heterogeneous graph structure is reliable. However, this assumption is usually unrealistic, since the heterogeneous graph in reality is inevitably noisy or incomplete. Therefore, it is vital to learn the heterogeneous graph structure for HGNNs rather than rely only on the raw graph structure. In light of this, we make the first attempt towards learning an optimal heterogeneous graph structure for HGNNs and propose a novel framework HGSL, which jointly performs Heterogeneous Graph Structure Learning and GNN parameters learning for classification task. Different from traditional GSL on homogeneous graph, considering the heterogeneity of different relations in heterogeneous graph, HGSL generates each relation subgraph independently. Specifically, in each generated relation subgraph, HGSL not only considers the feature similarity by generating feature similarity graph, but also considers the complex heterogeneous interactions in features and semantics by generating feature propagation graph and semantic graph. Then, these graphs are fused to a learned heterogeneous graph and optimized together with a GNN towards classification objective. Extensive experiments on real-world graphs demonstrate that the proposed framework significantly outperforms the state-of-the-art methods.