Recently,researchers extended 1-hop message passing to K-hop message passing by aggregating information fromK-hop neighbors of nodes simultaneously. However, there is no work on analyzing the expressive powerofK-hopmessagepassing.

In pioneering work from 2019, Barceló and coauthors identified logics that precisely match the expressive power of constant iteration-depth graph neural networks (GNNs) relative to properties definable in first-order logic. In this article, we give exact logical characterizations of recurrent GNNs in two scenarios: (1) in the setting with floating-point numbers and (2) with reals. For floats, the formalism matching recurrent GNNs is a rule-based modal logic with counting, while for reals we use a suitable infinitary modal logic, also with counting. These results give exact matches between logics and GNNs in the recurrent setting without rel-ativising to a background logic in either case, but using some natural assumptions about floating-point arithmetic. Applying our characterizations, we also prove that, relative to graph properties definable in monadic second-order logic (MSO), our infinitary and rule-based logics are equally expressive. This implies that recurrent GNNs with reals and floats have the same expressive power over MSO-definable properties and shows that, for such properties, also recurrent GNNs with reals are characterized by a (finitary!)

However, such an approach is highly empirical and provides an indirect evaluation affected by external factors.

Graph neural network (GNN) is a type of neural network that takes a graph as input.

Whenusedtomodelprobability distributions, theyexhibit tractable likelihoods and admit efficient learning algorithms.

Neural Information Processing Systems http://nips.cc/