Piecewise Constant Spectral Graph Neural Network
By: Vahan Martirosyan, Jhony H. Giraldo, Fragkiskos D. Malliaros
Potential Business Impact:
Helps computers learn better from messy, connected information.
Graph Neural Networks (GNNs) have achieved significant success across various domains by leveraging graph structures in data. Existing spectral GNNs, which use low-degree polynomial filters to capture graph spectral properties, may not fully identify the graph's spectral characteristics because of the polynomial's small degree. However, increasing the polynomial degree is computationally expensive and beyond certain thresholds leads to performance plateaus or degradation. In this paper, we introduce the Piecewise Constant Spectral Graph Neural Network(PieCoN) to address these challenges. PieCoN combines constant spectral filters with polynomial filters to provide a more flexible way to leverage the graph structure. By adaptively partitioning the spectrum into intervals, our approach increases the range of spectral properties that can be effectively learned. Experiments on nine benchmark datasets, including both homophilic and heterophilic graphs, demonstrate that PieCoN is particularly effective on heterophilic datasets, highlighting its potential for a wide range of applications.
Similar Papers
Spectral Graph Neural Networks are Incomplete on Graphs with a Simple Spectrum
Machine Learning (CS)
Makes AI better at understanding graph-like data.
LaguerreNet: Advancing a Unified Solution for Heterophily and Over-smoothing with Adaptive Continuous Polynomials
Machine Learning (CS)
Makes computer "brains" learn better from messy data.
Homomorphism Expressivity of Spectral Invariant Graph Neural Networks
Machine Learning (CS)
Makes computers understand complex patterns in data better.