Graph Few-Shot Learning via Adaptive Spectrum Experts and Cross-Set Distribution Calibration
This work addresses the challenge of rapidly adapting models to new tasks with limited labeled nodes in graph data, which is incremental as it builds on existing graph few-shot learning methods.
The paper tackles the problem of graph few-shot learning by addressing limitations of fixed graph filters and distribution mismatches between support and query sets, resulting in a proposed framework (GRACE) that consistently outperforms state-of-the-art baselines across various experimental settings.
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.