DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks
This addresses a fundamental limitation in GNNs for graph learning tasks, offering a novel method to improve expressiveness, though it is incremental in the context of GNN enhancements.
The paper tackles the limited expressiveness of standard graph neural networks (GNNs) by introducing DropGNNs, which use random node dropouts across multiple runs to enhance graph neighborhood discrimination, achieving competitive performance on established benchmarks.
This paper studies Dropout Graph Neural Networks (DropGNNs), a new approach that aims to overcome the limitations of standard GNN frameworks. In DropGNNs, we execute multiple runs of a GNN on the input graph, with some of the nodes randomly and independently dropped in each of these runs. Then, we combine the results of these runs to obtain the final result. We prove that DropGNNs can distinguish various graph neighborhoods that cannot be separated by message passing GNNs. We derive theoretical bounds for the number of runs required to ensure a reliable distribution of dropouts, and we prove several properties regarding the expressive capabilities and limits of DropGNNs. We experimentally validate our theoretical findings on expressiveness. Furthermore, we show that DropGNNs perform competitively on established GNN benchmarks.