DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks

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.

PDF Abstract NeurIPS 2021 PDF NeurIPS 2021 Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Graph Classification IMDb-B DropGIN Accuracy 75.7% # 11
Graph Classification IMDb-M DropGIN Accuracy 51.4% # 15
Graph Classification MUTAG DropGIN Accuracy 90.4% # 21
Graph Classification PROTEINS DropGIN Accuracy 76.3% # 45
Graph Classification PTC DropGIN Accuracy 66.3% # 19