Efficient Subgraph GNNs by Learning Effective Selection Policies

arXiv:2310.20082v2 Announce Type: replace
Abstract: Subgraph GNNs are provably expressive neural architectures that learn graph representations from sets of subgraphs. Unfortunately, their applicability is hampered by the computational complexity associated with performing message passing on many subgraphs. In this paper, we consider the problem of learning to select a small subset of the large set of possible subgraphs in a data-driven fashion. We first motivate the problem by proving that there are families of WL-indistinguishable graphs for which there exist …

abstract architectures arxiv complexity computational cs.lg gnns graph learn neural architectures paper small type