Cross-heterogeneity Graph Few-shot Learning

TL;DR

This paper introduces CGFL, a novel meta-learning model for cross-heterogeneity graph few-shot learning, effectively transferring knowledge across diverse heterogeneous graphs with different node and edge types.

Contribution

It proposes a new approach combining meta-pattern extraction, multi-view graph neural networks, and a score module for transferability, addressing the cross-heterogeneity scenario in few-shot learning.

Findings

CGFL outperforms state-of-the-art methods on four real-world datasets.

The model effectively captures heterogeneous information via meta-patterns.

It accurately measures transferability of source graphs for knowledge transfer.

Abstract

In recent years, heterogeneous graph few-shot learning has been proposed to address the label sparsity issue in heterogeneous graphs (HGs), which contain various types of nodes and edges. The existing methods have achieved good performance by transferring generalized knowledge extracted from rich-labeled classes in source HG(s) to few-labeled classes in a target HG. However, these methods only consider the single-heterogeneity scenario where the source and target HGs share a fixed set of node/edge types, ignoring the more general scenario of cross-heterogeneity, where each HG can have a different and non-fixed set of node/edge types. To this end, we focus on the unexplored cross-heterogeneity scenario and propose a novel model for Cross-heterogeneity Graph Few-shot Learning, namely CGFL. In CGFL, we first extract meta-patterns to capture heterogeneous information and propose a multi-view heterogeneous graph neural network (MHGN) to learn meta-patterns across HGs. Then, we propose a score module to measure the informativeness of labeled samples and determine the transferability of each source HG. Finally, by integrating MHGN and the score module into a meta-learning mechanism, CGFL can effectively transfer generalized knowledge to predict new classes with few-labeled data. Extensive experiments on four real-world datasets have demonstrated the superior performance of CGFL over the state-of-the-art methods.