Heterogeneous Graph Structure Learning for Graph Neural Networks

By Jianan Zhao, Xiao Wang, Chuan Shi, Binbin Hu, Guojie Song, Yanfang Ye. AAAI Conference on Artificial Intelligence, 2021

319 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/6e2bfca21d3c2bacb578b288148c3c1795b8c205

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yong Li
2. Yu Zheng
3. Jimmy X. Huang
4. Lianghao Xia
5. Yanan Niu
6. Jiashu Zhao
7. Chao Huang
8. Yiqun Hui

In Computer Vision and Pattern Recognition

1. Yu Zheng
2. Lianghao Xia
3. Chao Huang
4. Yang Song
5. Yong Li
6. Chen Gao
7. Depeng Jin
8. Dawei Yin

Citations in the corpus

• Sequential Recommendation with Graph Neural Networks (2021, methodology): “To balance expressiveness and complexity, we adopt weighted cosine similarity [5, 42] as our metric function formulated as follows,”
• Hypergraph Contrastive Collaborative Filtering (2022, background): “user misclick behaviors) to the constructed interaction graph [48].”