Handling Missing Data via Max-Entropy Regularized Graph Autoencoder

Graph neural networks (GNNs) are popular weapons for modeling relational data. Existing GNNs are not specified for attribute-incomplete graphs, making missing attribute imputation a burning issue. Until recently, many works notice that GNNs are coupled with spectral concentration, which means the spectrum obtained by GNNs concentrates on a local part in spectral domain, e.g., low-frequency due to oversmoothing issue. As a consequence, GNNs may be seriously flawed for reconstructing graph attributes as graph spectral concentration tends to cause a low imputation precision. In this work, we present a regularized graph autoencoder for graph attribute imputation, named MEGAE, which aims at mitigating spectral concentration problem by maximizing the graph spectral entropy. Notably, we first present the method for estimating graph spectral entropy without the eigen-decomposition of Laplacian matrix and provide the theoretical upper error bound. A maximum entropy regularization then acts in the latent space, which directly increases the graph spectral entropy. Extensive experiments show that MEGAE outperforms all the other state-of-the-art imputation methods on a variety of benchmark datasets.

Authors

• Ziqi Gao
• Yifan Niu The Hong Kong University of Science and Technology (Guangzhou)
• Jiashun Cheng The Hong Kong University of Science and Technology
• Jianheng Tang The Hong Kong University of Science and Technology
• Lanqing Li Tencent
• Tingyang Xu Tencent AI Lab
• Peilin Zhao Tencent AI Lab
• Fugee Tsung The Hong Kong University of Science and Technology (Guangzhou) The Hong Kong University of Science and Technology
• Jia Li School of Computer Science, Peking University MoE Key Lab. of High Confidence Software Technologies(PKU), China

Keywords

• ML: Graph-based Machine Learning