NEAR: Neighborhood Edge AggregatoR for Graph Classification
This work addresses a bottleneck in GNNs for graph classification, which is important for domains like bioinformatics and social network analysis, but it is incremental as it builds on existing methods like GIN.
The paper tackles the problem of information loss in graph neural networks (GNNs) that rely on 1-hop neighborhood message passing by proposing NEAR, a framework that aggregates edge relations in neighborhoods, and it shows improvements over existing 1-hop GNNs in graph classification tasks.
Learning graph-structured data with graph neural networks (GNNs) has been recently emerging as an important field because of its wide applicability in bioinformatics, chemoinformatics, social network analysis and data mining. Recent GNN algorithms are based on neural message passing, which enables GNNs to integrate local structures and node features recursively. However, past GNN algorithms based on 1-hop neighborhood neural message passing are exposed to a risk of loss of information on local structures and relationships. In this paper, we propose Neighborhood Edge AggregatoR (NEAR), a framework that aggregates relations between the nodes in the neighborhood via edges. NEAR, which can be orthogonally combined with Graph Isomorphism Network (GIN), gives integrated information that describes which nodes in the neighborhood are connected. Therefore, NEAR can reflect additional information of a local structure of each node beyond the nodes themselves in 1-hop neighborhood. Experimental results on multiple graph classification tasks show that our algorithm makes a good improvement over other existing 1-hop based GNN-based algorithms.