Deconvolutional Networks on Graph Data

In this paper, we consider an inverse problem in graph learning domain -- "given the graph representations smoothed by Graph Convolutional Network (GCN), how can we reconstruct the input graph signal? " We propose Graph Deconvolutional Network (GDN) and motivate the design of GDN via a combination of inverse filters in spectral domain and de-noising layers in wavelet domain, as the inverse operation results in a high frequency amplifier and may amplify the noise. We demonstrate the effectiveness of the proposed method on several tasks including graph feature imputation and graph structure generation.

Authors

• Jia Li School of Computer Science, Peking University MoE Key Lab. of High Confidence Software Technologies(PKU), China
• Jiajin Li
• Yang Liu College of Computer Science, Sichuan University Engineering Research Center of Machine Learning and Industry Intelligence, Ministry of Education
• Jianwei Yu Tencent AI Lab
• Yueting Li
• Hong Cheng

Keywords

No keywords are indexed for this paper.