Distributional Signals for Node Classification in Graph Neural Networks
This work addresses a gap in graph neural networks for semi-supervised node classification, offering a novel regularization method that is incremental in enhancing existing models.
The paper tackled the challenge of applying graph signal processing smoothness constraints to discrete node labels in graph neural networks by introducing distributional graph signals, which improved performance of base GNN models in semi-supervised node classification tasks.
In graph neural networks (GNNs), both node features and labels are examples of graph signals, a key notion in graph signal processing (GSP). While it is common in GSP to impose signal smoothness constraints in learning and estimation tasks, it is unclear how this can be done for discrete node labels. We bridge this gap by introducing the concept of distributional graph signals. In our framework, we work with the distributions of node labels instead of their values and propose notions of smoothness and non-uniformity of such distributional graph signals. We then propose a general regularization method for GNNs that allows us to encode distributional smoothness and non-uniformity of the model output in semi-supervised node classification tasks. Numerical experiments demonstrate that our method can significantly improve the performance of most base GNN models in different problem settings.