Towards Prototype-Based Self-Explainable Graph Neural Network

10/05/2022
by   Enyan Dai, et al.
0

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.

READ FULL TEXT
research
08/26/2021

Towards Self-Explainable Graph Neural Network

Graph Neural Networks (GNNs), which generalize the deep neural networks ...
research
12/02/2021

ProtGNN: Towards Self-Explaining Graph Neural Networks

Despite the recent progress in Graph Neural Networks (GNNs), it remains ...
research
05/31/2022

Concept-level Debugging of Part-Prototype Networks

Part-prototype Networks (ProtoPNets) are concept-based classifiers desig...
research
10/31/2022

PAGE: Prototype-Based Model-Level Explanations for Graph Neural Networks

Aside from graph neural networks (GNNs) catching significant attention a...
research
01/18/2022

High-Level Synthesis Performance Prediction using GNNs: Benchmarking, Modeling, and Advancing

Agile hardware development requires fast and accurate circuit quality ev...
research
08/29/2023

How Faithful are Self-Explainable GNNs?

Self-explainable deep neural networks are a recent class of models that ...
research
06/23/2023

TrustGuard: GNN-based Robust and Explainable Trust Evaluation with Dynamicity Support

Trust evaluation assesses trust relationships between entities and facil...

Please sign up or login with your details

Forgot password? Click here to reset