Virtual Node Tuning for Few-shot Node Classification
This work addresses a critical bottleneck in graph representation learning for scenarios with sparse or no labeled data in base classes, offering a novel solution that is incremental but impactful for domain-specific applications.
The paper tackles the challenge of Few-shot Node Classification (FSNC) when base classes have no or limited labeled nodes by proposing Virtual Node Tuning (VNT), which injects virtual nodes as soft prompts and includes a Graph-based Pseudo Prompt Evolution (GPPE) module, achieving superior performance on four datasets and outperforming state-of-the-art methods and fully supervised baselines.
Few-shot Node Classification (FSNC) is a challenge in graph representation learning where only a few labeled nodes per class are available for training. To tackle this issue, meta-learning has been proposed to transfer structural knowledge from base classes with abundant labels to target novel classes. However, existing solutions become ineffective or inapplicable when base classes have no or limited labeled nodes. To address this challenge, we propose an innovative method dubbed Virtual Node Tuning (VNT). Our approach utilizes a pretrained graph transformer as the encoder and injects virtual nodes as soft prompts in the embedding space, which can be optimized with few-shot labels in novel classes to modulate node embeddings for each specific FSNC task. A unique feature of VNT is that, by incorporating a Graph-based Pseudo Prompt Evolution (GPPE) module, VNT-GPPE can handle scenarios with sparse labels in base classes. Experimental results on four datasets demonstrate the superiority of the proposed approach in addressing FSNC with unlabeled or sparsely labeled base classes, outperforming existing state-of-the-art methods and even fully supervised baselines.