Homomorphism Counts for Graph Neural Networks: All About That Basis

A large body of work has investigated the properties of graph neural networks and identified several limitations, particularly pertaining to their expressive power. Their inability to count certainpatterns(e.g., cycles) in a graph lies at the heart of such limitations, since many functions to be learned rely on the ability of counting such patterns. Two prominent paradigms aim to address this limitation by enriching the graph features withsubgraphorhomomorphismpattern counts. In this work, we show that both of these approaches are sub-optimal in a certain sense and argue for a morefine-grainedapproach, which incorporates the homomorphism counts ofallstructures in the ``basis'' of the target pattern. This yields strictly more expressive architectures without incurring any additional overhead in terms of computational complexity compared to existing approaches. We prove a series of theoretical results on node-level and graph-levelmotif parametersand empirically validate them on standard benchmark datasets.