IEEE

On the Identification of Isomorphic Graphs for Graph Neural Network using Multi-graph Approach

Abstract: The Graph Isomorphism problem regained interest with the rise of Graph Neural Networks (GNN). These GNN models have limited ability to distinguish between isomorphic graphs and hence their ...
IEEE

Graph Neural Networks With Parallel Neighborhood Aggregations for Graph Classification

Abstract: We focus on graph classification using a graph neural network (GNN) model that precomputes node features using a bank of neighborhood aggregation graph operators arranged in parallel. These ...