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

2026-04-30

AI Summary

This work addresses the limitations of existing graph few-shot learning methods, which struggle to model hierarchical graph structures in Euclidean space and suffer from biased support set distributions during meta-testing, leading to poor generalization. To overcome these challenges, we propose a novel meta-learning framework that uniquely integrates hyperbolic geometry with a denoising diffusion mechanism. By leveraging the innate ability of hyperbolic space to capture hierarchical relationships and employing a diffusion model to enrich and debias the support set distribution, our approach achieves improved generalization. Theoretical analysis demonstrates that the proposed method yields a tighter generalization bound, while extensive experiments on multiple benchmark datasets show significant gains in both accuracy and robustness over state-of-the-art methods.

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.

Problem

• graph few-shot learning
• hierarchical structure
• support distribution
• Euclidean space
• true underlying distribution

Innovation

• hyperbolic space
• denoising diffusion
• graph few-shot learning
• meta-learning
• hierarchical structure