Few-shot Node Classification with Extremely Weak Supervision

TL;DR

This paper introduces X-FNC, a meta-learning framework designed for few-shot node classification under extremely weak supervision, effectively leveraging pseudo-labeled nodes to improve generalization on real-world graphs with scarce labeled data.

Contribution

The paper proposes a novel framework X-FNC that addresses the challenge of extremely weak supervision in few-shot node classification by incorporating pseudo-labeling and meta-learning techniques.

Findings

X-FNC outperforms state-of-the-art baselines on four datasets.

Pseudo-labeling significantly improves classification accuracy.

The framework effectively generalizes from scarce labeled nodes.

Abstract

Few-shot node classification aims at classifying nodes with limited labeled nodes as references. Recent few-shot node classification methods typically learn from classes with abundant labeled nodes (i.e., meta-training classes) and then generalize to classes with limited labeled nodes (i.e., meta-test classes). Nevertheless, on real-world graphs, it is usually difficult to obtain abundant labeled nodes for many classes. In practice, each meta-training class can only consist of several labeled nodes, known as the extremely weak supervision problem. In few-shot node classification, with extremely limited labeled nodes for meta-training, the generalization gap between meta-training and meta-test will become larger and thus lead to suboptimal performance. To tackle this issue, we study a novel problem of few-shot node classification with extremely weak supervision and propose a principled framework X-FNC under the prevalent meta-learning framework. Specifically, our goal is to accumulate meta-knowledge across different meta-training tasks with extremely weak supervision and generalize such knowledge to meta-test tasks. To address the challenges resulting from extremely scarce labeled nodes, we propose two essential modules to obtain pseudo-labeled nodes as extra references and effectively learn from extremely limited supervision information. We further conduct extensive experiments on four node classification datasets with extremely weak supervision to validate the superiority of our framework compared to the state-of-the-art baselines.