Global explanation supervision for Graph Neural Networks
Frontiers in Big Data · 01.07.2024 · 7
DOI: 10.3389/fdata.2024.1410424 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Big Data, online erschienen am 01.07.2024. Verfasst von Negar Etemadyrad und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, George Mason University, Fairfax, VA, United States. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
With the increasing popularity of Graph Neural Networks (GNNs) for predictive tasks on graph structured data, research on their explainability is becoming more critical and achieving significant progress. Although many methods are proposed to explain the predictions of GNNs, their focus is mainly on “how to generate explanations.” However, other important research questions like “whether the GNN explanations are inaccurate,” “what if the explanations are inaccurate,” and “how to adjust the model to generate more accurate explanations” have gained little attention. Our previous GNN Explanation Supervision (GNES) framework demonstrated effectiveness on improving the reasonability of the local explanation while still keep or even improve the backbone GNNs model performance. In many applications instead of per sample explanations, we need to find global explanations which are reasonable and faithful to the domain data. Simply learning to explain GNNs locally is not an optimal solution to a global understanding of the model. To improve the explainability power of the GNES framework, we propose the Global GNN Explanation Supervision (GGNES) technique which uses a basic trained GNN and a global extension of the loss function used in the GNES framework. This GNN creates local explanations which are fed to a Global Logic-based GNN Explainer, an existing technique that can learn the global Explanation in terms of a logic formula. These two frameworks are then trained iteratively to generate reasonable global explanations. Extensive experiments demonstrate the effectiveness of the proposed model on improving the global explanations while keeping the performance similar or even increase the model prediction power.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Electrical and Computer Engineering, George Mason University, Fairfax, VA, United States.
- Department of Computer Science, Emory University, Atlanta, GA, United States.
Zitieren
APA
Etemadyrad, N., Gao, Y., Manoj Pudukotai Dinakarrao, S., & Zhao, L. (2024). Global explanation supervision for Graph Neural Networks. Frontiers in Big Data, 7. https://doi.org/10.3389/fdata.2024.1410424
Vancouver
Etemadyrad N, Gao Y, Manoj Pudukotai Dinakarrao S, Zhao L. Global explanation supervision for Graph Neural Networks. Frontiers in Big Data. 2024;7. doi:10.3389/fdata.2024.1410424
BibTeX
@article{Etemadyrad2024,
author = {Etemadyrad, Negar and Gao, Yuyang and Manoj Pudukotai Dinakarrao, Sai and Zhao, Liang},
title = {Global explanation supervision for Graph Neural Networks},
journal = {Frontiers in Big Data},
year = {2024},
volume = {7},
doi = {10.3389/fdata.2024.1410424}
}
EUVIMED