Improving Graph Few-shot Learning with Hyperbolic Space and Denoising Diffusion

TL;DR

This paper introduces IMPRESS, a framework that enhances graph few-shot learning by using hyperbolic space for better hierarchical representation and denoising diffusion to refine support distributions, resulting in improved performance.

Contribution

The paper proposes a novel graph few-shot learning method that employs hyperbolic space and denoising diffusion, addressing limitations of Euclidean representations and distribution fitting.

Findings

IMPRESS outperforms baselines on multiple benchmarks.

Theoretical analysis shows tighter generalization bounds.

Representation in hyperbolic space captures hierarchical graph structures.

Abstract

Graph few-shot learning, which focuses on effectively learning from only a small number of labeled nodes to quickly adapt to new tasks, has garnered significant research attention. Despite recent advances in graph few-shot learning that have demonstrated promising performance, existing methods still suffer from several key limitations. First, during the meta-training phase, these methods typically perform node representation learning in Euclidean space, which often fails to capture the inherently hierarchical structure existing in real-world graph data. Second, during the meta-testing phase, they usually fit an empirical target distribution derived from only a few support samples, even when this distribution significantly deviates from the true underlying distribution. To address these issues, we propose IMPRESS, a novel framework that IMproves graPh few-shot learning with hypeRbolic spacE and denoiSing diffuSion. Specifically, our model learns node representations in a hyperbolic space and enriches the support distribution through denoising diffusion mechanisms. Theoretically, IMPRESS achieves a tighter generalization bound. Empirically, IMPRESS consistently outperforms competitive baselines across multiple benchmark datasets.