Unsupervised Episode Generation for Graph Meta-learning

TL;DR

This paper introduces NaQ, an unsupervised episode generation method for graph meta-learning, enabling effective few-shot node classification without labeled data by simulating task-specific episodes.

Contribution

NaQ is a simple, model-agnostic unsupervised episode generation approach that improves graph meta-learning for FSNC by utilizing all nodes and incorporating task-awareness.

Findings

NaQ enhances performance of existing meta-learning methods in FSNC.

NaQ effectively utilizes all nodes in a graph for unsupervised learning.

NaQ sometimes outperforms supervised episode generation methods.

Abstract

We propose Unsupervised Episode Generation method called Neighbors as Queries (NaQ) to solve the Few-Shot Node-Classification (FSNC) task by unsupervised Graph Meta-learning. Doing so enables full utilization of the information of all nodes in a graph, which is not possible in current supervised meta-learning methods for FSNC due to the label-scarcity problem. In addition, unlike unsupervised Graph Contrastive Learning (GCL) methods that overlook the downstream task to be solved at the training phase resulting in vulnerability to class imbalance of a graph, we adopt the episodic learning framework that allows the model to be aware of the downstream task format, i.e., FSNC. The proposed NaQ is a simple but effective unsupervised episode generation method that randomly samples nodes from a graph to make a support set, followed by similarity-based sampling of nodes to make the corresponding query set. Since NaQ is model-agnostic, any existing supervised graph meta-learning methods can be trained in an unsupervised manner, while not sacrificing much of their performance or sometimes even improving them. Extensive experimental results demonstrate the effectiveness of our proposed unsupervised episode generation method for graph meta-learning towards the FSNC task. Our code is available at: https://github.com/JhngJng/NaQ-PyTorch.