Shape-aware Graph Spectral Learning
This work addresses a gap in spectral GNNs for graph learning tasks, offering a method to better handle diverse graph structures, though it is incremental by building on existing spectral filter approaches.
The paper tackles the problem of spectral GNNs not systematically considering the relationship between graph frequency and homophily/heterophily levels, and proposes a shape-aware regularization method that achieves superior performance on both homophilous and heterophilous datasets, with NewtonNet demonstrating improved results across benchmarks.
Spectral Graph Neural Networks (GNNs) are gaining attention for their ability to surpass the limitations of message-passing GNNs. They rely on supervision from downstream tasks to learn spectral filters that capture the graph signal's useful frequency information. However, some works empirically show that the preferred graph frequency is related to the graph homophily level. This relationship between graph frequency and graphs with homophily/heterophily has not been systematically analyzed and considered in existing spectral GNNs. To mitigate this gap, we conduct theoretical and empirical analyses revealing a positive correlation between low-frequency importance and the homophily ratio, and a negative correlation between high-frequency importance and the homophily ratio. Motivated by this, we propose shape-aware regularization on a Newton Interpolation-based spectral filter that can (i) learn an arbitrary polynomial spectral filter and (ii) incorporate prior knowledge about the desired shape of the corresponding homophily level. Comprehensive experiments demonstrate that NewtonNet can achieve graph spectral filters with desired shapes and superior performance on both homophilous and heterophilous datasets.