Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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

About

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.

Yonghao Liu, Jialu Sun, Wei Pang, Fausto Giunchiglia, Ximing Li, Xiaoyue Feng, Renchu Guan• 2026

Related benchmarks

TaskDatasetResultRank
Node ClassificationCora
Accuracy90.8
583
Node ClassificationCora-ML
Accuracy97.63
326
few-shot node classificationCoraFull
Accuracy86.63
68
few-shot node classificationCoauther CS
Accuracy97.97
68
Node Classificationogbn-arxiv (test)
Accuracy (5-way 3-shot)61.11
15
Showing 5 of 5 rows

Other info

Follow for update