| dc.description.abstract | Subgraph classification is an emerging field in graph representation learning where the task is to classify a group of nodes (i.e., a subgraph) within a graph. Graph neural networks (GNNs) are the de facto solution for node, link, and graph-level tasks but fail to perform well on subgraph classification tasks. Even GNNs tailored for graph classification are not directly transferable to subgraph classification as they ignore the external topology of the subgraph, thus failing to capture how the subgraph is located within the larger graph. Existing models for subgraph classification address this shortcoming through labeling tricks or multiple message-passing channels, both of which impose a computation burden and are not scalable to large graphs. To address the scalability issue while maintaining generalization, we propose Stochastic Subgraph Neighborhood Pooling (SSNP), which jointly aggregates the subgraph and its neighborhood (i.e., external topology) information without any computationally expensive operations such as labeling tricks. To improve scalability and generalization further, we also propose a simple data augmentation pre-processing step for SSNP that creates multiple sparse views of the subgraph neighborhood. We show that our model is more expressive than plain GNNs, without using any labeling tricks. Our extensive experiments demonstrate that our models outperform current state-of-the art methods (with a margin of up to 2%) while being up to 3× faster in training. | en |
