Hierarchical Diffusion Scattering Graph Neural Network

Graph neural network (GNN) is popular now to solve the tasks in non-Euclidean space and most of them learn deep embeddings by aggregating the neighboring nodes. However, these methods are prone to some problems such as over-smoothing because of the single-scale perspective field and the nature of low-pass filter. To address these limitations, we introduce diffusion scattering network (DSN) to exploit high-order patterns. With observing the complementary relationship between multi-layer GNN and DSN, we propose Hierarchical Diffusion Scattering Graph Neural Network (HDS-GNN) to efficiently bridge DSN and GNN layer by layer to supplement GNN with multi-scale information and band-pass signals. Our model extracts node-level scattering representations by intercepting the low-pass filtering, and adaptively tunes the different scales to regularize multi-scale information. Then we apply hierarchical representation enhancement to improve GNN with the scattering features. We benchmark our model on nine real-world networks on the transductive semi-supervised node classification task. The experimental results demonstrate the effectiveness of our method.

Authors

• Ke Zhang Hangzhou Dianzi University
• Xinyan Pu
• Jiaxing Li Southeast University
• Jiasong Wu Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University) Centre de Recherche en Information Biomédicale Sino-français (CRIBs) Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing (Southeast University)
• Huazhong Shu Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University) Centre de Recherche en Information Biomédicale Sino-français (CRIBs) Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing (Southeast University)
• Youyong Kong

Keywords

• Data Mining: Mining Graphs
• Machine Learning: Geometric Learning
• Machine Learning: Representation learning
• Machine Learning: Semi-Supervised Learning