Abstract:Solving parity games is a major building block for numerous applications in reactive program verification and synthesis. While there exist efficient approaches to solving parity games in practice, none of these have a polynomial worst-case runtime complexity. We present a incomplete approach to determining the winning regions of parity games via graph neural networks. Our evaluation on 900 randomly generated parity games shows that this approach is efficient in practice. It moreover correctly determines the winning regions of ~60% of the games in our data set and only incurs minor errors in the remaining ones.