Predicting Winning Regions in Parity Games via Graph Neural Networks

Tobias Hecking, Swathi Muthukrishnan, Alexander Weinert

Keywords: Graph Neural Networks, Parity Games, Computer Aided Verification

Abstract:

Solving parity games is a major building block for numerous
applications in reactive program verification and synthesis.
While they can be solved efficiently in practice, no known
approach has a polynomial worst-case runtime complexity.
We present a incomplete polynomial-time approach to de-
termining the winning regions of parity games via graph
neural networks.
Our evaluation on 900 randomly generated parity games
shows that this approach is effective and efficient in prac-
tice. It correctly determines the winning regions of ∼60% of
the games in our data set and only incurs minor errors in
the remaining ones. We believe that this approach can be
extended to efficiently solve parity games as well.