BAED: a New Paradigm for Few-shot Graph Learning with Explanation in the Loop

TL;DR

BAED introduces an explanation-in-the-loop framework for few-shot graph learning, enhancing prediction accuracy and interpretability by leveraging belief propagation and auxiliary neural networks to focus on informative subgraphs.

Contribution

This work pioneers the integration of explanation mechanisms into FSGL, employing belief propagation and auxiliary GNNs to improve robustness and interpretability.

Findings

Superior accuracy on seven benchmark datasets

Enhanced training efficiency compared to existing methods

High-quality explanations through subgraph extraction

Abstract

The challenges of training and inference in few-shot environments persist in the area of graph representation learning. The quality and quantity of labels are often insufficient due to the extensive expert knowledge required to annotate graph data. In this context, Few-Shot Graph Learning (FSGL) approaches have been developed over the years. Through sophisticated neural architectures and customized training pipelines, these approaches enhance model adaptability to new label distributions. However, compromises in \textcolor{black}{the model's} robustness and interpretability can result in overfitting to noise in labeled data and degraded performance. This paper introduces the first explanation-in-the-loop framework for the FSGL problem, called BAED. We novelly employ the belief propagation algorithm to facilitate label augmentation on graphs. Then, leveraging an auxiliary graph neural network and the gradient backpropagation method, our framework effectively extracts explanatory subgraphs surrounding target nodes. The final predictions are based on these informative subgraphs while mitigating the influence of redundant information from neighboring nodes. Extensive experiments on seven benchmark datasets demonstrate superior prediction accuracy, training efficiency, and explanation quality of BAED. As a pioneer, this work highlights the potential of the explanation-based research paradigm in FSGL.