Graph few-shot learning has attracted increasing attention due to its ability to rapidly adapt models to new tasks with only limited labeled nodes. Despite the remarkable progress made by existing graph few-shot learning methods, several key limitations remain. First, most current approaches rely on predefined and unified graph filters (e.g., low-pass or high-pass filters) to globally enhance or suppress node frequency signals. Such fixed spectral operations fail to account for the heterogeneity of local topological structures inherent in real-world graphs. Moreover, these methods often assume that the support and query sets are drawn from the same distribution. However, under few-shot conditions, the limited labeled data in the support set may not sufficiently capture the complex distribution of the query set, leading to suboptimal generalization. To address these challenges, we propose GRACE, a novel Graph few-shot leaRning framework that integrates Adaptive spectrum experts with Cross-sEt distribution calibration techniques. Theoretically, the proposed approach enhances model generalization by adapting to both local structural variations and cross-set distribution calibration. Empirically, GRACE consistently outperforms state-of-the-art baselines across a wide range of experimental settings. Our code can be found here.

翻译：图小样本学习因其能够仅利用有限标记节点使模型快速适应新任务而受到越来越多的关注。尽管现有图小样本学习方法已取得显著进展，但仍存在若干关键局限。首先，当前大多数方法依赖预定义且统一的图滤波器（例如低通或高通滤波器）来全局增强或抑制节点频率信号。此类固定的频谱操作未能考虑现实世界图中固有的局部拓扑结构异质性。此外，这些方法通常假设支持集与查询集源自相同分布。然而在小样本条件下，支持集中有限的标记数据可能不足以捕捉查询集的复杂分布，导致次优的泛化性能。为应对这些挑战，我们提出GRACE——一种整合自适应频谱专家与跨集分布校准技术的新型图小样本学习框架。理论上，该方法通过同时适应局部结构变化与跨集分布校准来增强模型泛化能力。实证表明，GRACE在广泛的实验设置中持续优于现有先进基线方法。我们的代码可见此处。