Inductive Linear Probing for Few-shot Node Classification
This work addresses a gap in graph-based few-shot learning for researchers, but it is incremental as it focuses on adapting known methods to a specific setting.
The paper tackles the problem of few-shot node classification in graphs by highlighting the limitations of existing meta-learning methods in the inductive setting and proposes a simple baseline approach for this task, showing competitive performance.
Meta-learning has emerged as a powerful training strategy for few-shot node classification, demonstrating its effectiveness in the transductive setting. However, the existing literature predominantly focuses on transductive few-shot node classification, neglecting the widely studied inductive setting in the broader few-shot learning community. This oversight limits our comprehensive understanding of the performance of meta-learning based methods on graph data. In this work, we conduct an empirical study to highlight the limitations of current frameworks in the inductive few-shot node classification setting. Additionally, we propose a simple yet competitive baseline approach specifically tailored for inductive few-shot node classification tasks. We hope our work can provide a new path forward to better understand how the meta-learning paradigm works in the graph domain.