Handling Missing Data via Max-Entropy Regularized Graph Autoencoder
Keywords:ML: Graph-based Machine Learning
AbstractGraph 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.
How to Cite
Gao, Z., Niu, Y., Cheng, J., Tang, J., Li, L., Xu, T., Zhao, P., Tsung, F., & Li, J. (2023). Handling Missing Data via Max-Entropy Regularized Graph Autoencoder. Proceedings of the AAAI Conference on Artificial Intelligence, 37(6), 7651-7659. https://doi.org/10.1609/aaai.v37i6.25928
AAAI Technical Track on Machine Learning I