PlanE: Representation Learning over Planar Graphs

by   Radoslav Dimitrov, et al.

Graph neural networks are prominent models for representation learning over graphs, where the idea is to iteratively compute representations of nodes of an input graph through a series of transformations in such a way that the learned graph function is isomorphism invariant on graphs, which makes the learned representations graph invariants. On the other hand, it is well-known that graph invariants learned by these class of models are incomplete: there are pairs of non-isomorphic graphs which cannot be distinguished by standard graph neural networks. This is unsurprising given the computational difficulty of graph isomorphism testing on general graphs, but the situation begs to differ for special graph classes, for which efficient graph isomorphism testing algorithms are known, such as planar graphs. The goal of this work is to design architectures for efficiently learning complete invariants of planar graphs. Inspired by the classical planar graph isomorphism algorithm of Hopcroft and Tarjan, we propose PlanE as a framework for planar representation learning. PlanE includes architectures which can learn complete invariants over planar graphs while remaining practically scalable. We empirically validate the strong performance of the resulting model architectures on well-known planar graph benchmarks, achieving multiple state-of-the-art results.


page 1

page 2

page 3

page 4


Homothetic triangle representations of planar graphs

We prove that every planar graph is the intersection graph of homothetic...

On Optimal Beyond-Planar Graphs

A graph is beyond-planar if it can be drawn in the plane with a specific...

Cops and Robbers on 1-Planar Graphs

Cops and Robbers is a well-studied pursuit-evasion game in which a set o...

An Experimental Study of a 1-planarity Testing and Embedding Algorithm

The definition of 1-planar graphs naturally extends graph planarity, nam...

Learning Invariant Representations Of Planar Curves

We propose a metric learning framework for the construction of invariant...

PHOEG Helps Obtaining Extremal Graphs

Extremal Graph Theory aims to determine bounds for graph invariants as w...

Neural Networks on Random Graphs

We performed a massive evaluation of neural networks with architectures ...

Please sign up or login with your details

Forgot password? Click here to reset