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

TL;DR

This paper introduces the first explanation-in-the-loop framework for the FSGL problem, called BAED, which employs the belief propagation algorithm to facilitate label augmentation on graphs and effectively extracts explanatory subgraphs surrounding target nodes.

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.

Figures (7)

• Figure 1: Explanation in the loop: a new paradigm for FSGL
• Figure 2: BAED: the explanation-based FSGL pipeline
• Figure 3: Explanatory subgraphs extracted using gradient backpropagation and edge ranking on the PubMed.Colored backgrounds (red, green, blue) indicate ground-truth node labels; gray nodes are unlabeled. Dashed circles denote the explanatory subgraphs for node A, B, and C, with edge numbers indicating importance rankings. Nodes A and B lie within homogeneous regions of same-label nodes, resulting in clean subgraphs without distracting connections. Node C, positioned near both red and blue nodes, yields a mixed but predominantly blue subgraph, leading to a correct prediction.
• Figure 4: Classification accuracy with different labeling ratios
• Figure 5: Convergence Curves of BP Process in Label Augmentation. Legend denotes [dataset, No. converged iteration]

Theorems & Definitions (2)

• Definition 1
• Definition 2