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

arXiv cs.LG / 5/1/2026

📰 NewsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper introduces IMPRESS, a framework to improve graph few-shot learning by addressing limitations in existing methods during both meta-training and meta-testing.
It proposes learning node representations in hyperbolic space to better model the hierarchical structure commonly found in real-world graphs.
It enhances the support (target) distribution used at meta-testing by applying denoising diffusion mechanisms, aiming to better approximate the underlying true distribution.
The authors report theoretical gains in generalization via a tighter generalization bound and show empirical improvements over multiple benchmark baselines.
Overall, IMPRESS combines geometry (hyperbolic embeddings) and generative denoising to make few-shot adaptation more reliable for graph tasks.

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.