Few-Shot Learning on Graphs via Super-Classes based on Graph Spectral Measures
This addresses the problem of limited labeled data for graph classification in machine learning, though it appears incremental as it builds on existing GNN frameworks with a novel clustering approach.
The paper tackles few-shot graph classification by clustering graphs into super-classes using spectral measures and Wasserstein distance, then using a super-graph to improve class separation in GNNs, resulting in outperformance over state-of-the-art methods and baseline GNNs in empirical evaluations.
We propose to study the problem of few shot graph classification in graph neural networks (GNNs) to recognize unseen classes, given limited labeled graph examples. Despite several interesting GNN variants being proposed recently for node and graph classification tasks, when faced with scarce labeled examples in the few shot setting, these GNNs exhibit significant loss in classification performance. Here, we present an approach where a probability measure is assigned to each graph based on the spectrum of the graphs normalized Laplacian. This enables us to accordingly cluster the graph base labels associated with each graph into super classes, where the Lp Wasserstein distance serves as our underlying distance metric. Subsequently, a super graph constructed based on the super classes is then fed to our proposed GNN framework which exploits the latent inter class relationships made explicit by the super graph to achieve better class label separation among the graphs. We conduct exhaustive empirical evaluations of our proposed method and show that it outperforms both the adaptation of state of the art graph classification methods to few shot scenario and our naive baseline GNNs. Additionally, we also extend and study the behavior of our method to semi supervised and active learning scenarios.