Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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

Renchu Guan, Yajun Wang, Chunli Guo, Bowen Cao, Fausto Giunchiglia, Wei Pang, Yonghao Liu, Xiaoyue Feng• 2026

Related benchmarks

TaskDatasetResultRank
Node ClassificationCiteseer
Accuracy77.78
503
Node ClassificationCora-ML
Accuracy93.71
326
Node ClassificationOgbn-arxiv
Accuracy66.62
304
Node ClassificationCoraFull 5-way 3-shot (test)
Accuracy80.23
36
Node ClassificationCoraFull 5 way 5 shot
Accuracy83.02
20
Node ClassificationCoraFull 10 way 3 shot
Accuracy70.73
20
Node ClassificationCoraFull 10 way 5 shot
Accuracy73.64
20
Node ClassificationCora 2 way 1 shot
Accuracy76.11
20
Node ClassificationCora 2 way 3 shot
Accuracy (%)82.72
20
Node ClassificationCora 2 way 5 shot
Accuracy (%)86.02
20
Showing 10 of 14 rows

Other info

Follow for update