Analysis of Corrected Graph Convolutions

Understand

Machine learning for node classification on graphs is a prominent area driven by applications such as recommendation systems.

• State-of-the-art models often use multiple graph convolutions on the data, as empirical evidence suggests they can enhance performance.
• However, it has been shown empirically and theoretically, that too many graph convolutions can degrade performance significantly, a phenomenon known as oversmoothing.
• In this paper, we provide a rigorous theoretical analysis, based on the two-class contextual stochastic block model (CSBM), of the performance of vanilla graph convolution from which we remove the principal eigenvector to avoid oversmoothing.