LGAIOct 5, 2022

Towards Prototype-Based Self-Explainable Graph Neural Network

arXiv:2210.01974v124 citationsh-index: 20
Originality Incremental advance
AI Analysis

This addresses the problem of trust and adoption in high-stake scenarios for users of GNNs, though it is incremental as it builds on limited prior work on self-explainable GNNs.

The paper tackles the lack of interpretability in Graph Neural Networks (GNNs) by proposing a prototype-based self-explainable GNN framework that simultaneously provides accurate predictions and prototype-based explanations, with experiments showing effectiveness in both prediction accuracy and explanation quality on real-world and synthetic datasets.

Graph Neural Networks (GNNs) have shown great ability in modeling graph-structured data for various domains. However, GNNs are known as black-box models that lack interpretability. Without understanding their inner working, we cannot fully trust them, which largely limits their adoption in high-stake scenarios. Though some initial efforts have been taken to interpret the predictions of GNNs, they mainly focus on providing post-hoc explanations using an additional explainer, which could misrepresent the true inner working mechanism of the target GNN. The works on self-explainable GNNs are rather limited. Therefore, we study a novel problem of learning prototype-based self-explainable GNNs that can simultaneously give accurate predictions and prototype-based explanations on predictions. We design a framework which can learn prototype graphs that capture representative patterns of each class as class-level explanations. The learned prototypes are also used to simultaneously make prediction for for a test instance and provide instance-level explanation. Extensive experiments on real-world and synthetic datasets show the effectiveness of the proposed framework for both prediction accuracy and explanation quality.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes