Node Masking: Making Graph Neural Networks Generalize and Scale Better
This work addresses scalability and generalization issues in GNNs for researchers and practitioners, though it appears incremental as it builds on existing spatial architectures.
The paper tackled the problem of improving generalization and scalability in Graph Neural Networks (GNNs) by introducing Node Masking, a simple concept analyzed through theoretical tools, and validated it with experiments on node classification datasets in transductive and inductive settings, achieving strong benchmarks.
Graph Neural Networks (GNNs) have received a lot of interest in the recent times. From the early spectral architectures that could only operate on undirected graphs per a transductive learning paradigm to the current state of the art spatial ones that can apply inductively to arbitrary graphs, GNNs have seen significant contributions from the research community. In this paper, we utilize some theoretical tools to better visualize the operations performed by state of the art spatial GNNs. We analyze the inner workings of these architectures and introduce a simple concept, Node Masking, that allows them to generalize and scale better. To empirically validate the concept, we perform several experiments on some widely-used datasets for node classification in both the transductive and inductive settings, hence laying down strong benchmarks for future research.