Advancing Graph Few-Shot Learning via In-Context Learning
About
Graph few-shot learning, which aims to classify nodes from novel classes with only a few labeled examples, is a widely studied problem in graph learning. However, existing methods often face two key limitations. First, the predominant graph few-shot learning paradigm relies on supervised tasks, failing to leverage the vast number of unlabeled nodes in the graph. Second, many approaches require complex task adaptation or fine-tuning during inference, limiting their efficiency and applicability. Inspired by the powerful in-context learning capabilities of large language models, we propose a novel model named VISION for adVancIng graph few-Shot learning via In-cOntext LearNing to address these challenges. Our model reframes graph few-shot learning as a fine-tuning-free sequence reasoning problem. At its core is a context-aware network that initializes nodes with role embeddings and employs a dual-context fusion module to synergistically integrate local topological structures and global task-level dependencies. This allows our model to dynamically generate class-aware representations for the query set conditioned on the support set context in a single forward pass. To effectively train our model, we introduce an unsupervised task generator that creates structure-adaptive features and constructs diverse pseudo-tasks from abundant unlabeled data. Our method unifies unsupervised meta-learning with graph in-context learning, achieving efficient inference. Extensive experiments on multiple benchmark datasets demonstrate the superiority of our model. Our public code can be found
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Node Classification | Citeseer | Accuracy77.78 | 503 | |
| Node Classification | Cora-ML | Accuracy93.71 | 326 | |
| Node Classification | Ogbn-arxiv | Accuracy66.62 | 304 | |
| Node Classification | CoraFull 5-way 3-shot (test) | Accuracy80.23 | 36 | |
| Node Classification | CoraFull 5 way 5 shot | Accuracy83.02 | 20 | |
| Node Classification | CoraFull 10 way 3 shot | Accuracy70.73 | 20 | |
| Node Classification | CoraFull 10 way 5 shot | Accuracy73.64 | 20 | |
| Node Classification | Cora 2 way 1 shot | Accuracy76.11 | 20 | |
| Node Classification | Cora 2 way 3 shot | Accuracy (%)82.72 | 20 | |
| Node Classification | Cora 2 way 5 shot | Accuracy (%)86.02 | 20 |