Virtual Node Tuning for Few-shot Node Classification

2023/06/09 by Zhen Tan, Ruocheng Guo, Tan, Zhen +5 · 5 citations
Computer Science · #Advanced Graph Neural Networks #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2306.06063

openalex publication_date 2023/06/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• Dynamic Graph Recommendation via Sparse Augmentation and Singular Adaptation
• Graph Prompting for Graph Learning Models: Recent Advances and Future Directions
• Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning
• HGMP:Heterogeneous Graph Multi-Task Prompt Learning
• PLACE: Prompt Learning for Attributed Community Search in Large Graphs

Related

• Contrastive Meta-Learning for Few-shot Node Classification
• Virtual Node Generation for Node Classification in Sparsely-Labeled Graphs
• Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embedding
• Graph Prototypical Networks for Few-shot Learning on Attributed Networks
• Meta-GNN: On Few-shot Node Classification in Graph Meta-learning