Few-Shot Causal Representation Learning for Out-of-Distribution Generalization on Heterogeneous Graphs

arXiv:2401.03597v2 Announce Type: replace
Abstract: Heterogeneous graph few-shot learning (HGFL) has been developed to address the label sparsity issue in heterogeneous graphs (HGs), which consist of various types of nodes and edges. The core concept of HGFL is to extract knowledge from rich-labeled classes in a source HG, transfer this knowledge to a target HG to facilitate learning new classes with few-labeled training data, and finally make predictions on unlabeled testing data. Existing methods typically assume that the source HG, …

abstract arxiv causal concept core cs.ai cs.lg distribution extract few-shot few-shot learning graph graphs issue knowledge nodes representation representation learning sparsity transfer type types