FlowX: Towards Explainable Graph Neural Networks via Message Flows
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-07 · 46 (7) · 4567-4578
DOI: 10.1109/tpami.2023.3347470 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-07. Verfasst von Shurui Gui und 5 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 64 Literaturangaben.
Abstract (Originalsprache)
We investigate the explainability of graph neural networks (GNNs) as a step toward elucidating their working mechanisms. While most current methods focus on explaining graph nodes, edges, or features, we argue that, as the inherent functional mechanism of GNNs, message flows are more natural for performing explainability. To this end, we propose a novel method here, known as FlowX, to explain GNNs by identifying important message flows. To quantify the importance of flows, we propose to follow the philosophy of Shapley values from cooperative game theory. To tackle the complexity of computing all coalitions' marginal contributions, we propose a flow sampling scheme to compute Shapley value approximations as initial assessments of further training. We then propose an information-controlled learning algorithm to train flow scores toward diverse explanation targets: necessary or sufficient explanations. Experimental studies on both synthetic and real-world datasets demonstrate that our proposed FlowX and its variants lead to improved explainability of GNNs.
Zitieren
APA
Gui, S., Yuan, H., Wang, J., Lao, Q., Li, K., & Ji, S. (2024). FlowX: Towards Explainable Graph Neural Networks via Message Flows. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(7), 4567-4578. https://doi.org/10.1109/tpami.2023.3347470
Vancouver
Gui S, Yuan H, Wang J, Lao Q, Li K, Ji S. FlowX: Towards Explainable Graph Neural Networks via Message Flows. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(7):4567-4578. doi:10.1109/tpami.2023.3347470
BibTeX
@article{Gui2024,
author = {Gui, Shurui and Yuan, Hao and Wang, Jie and Lao, Qicheng and Li, Kang and Ji, Shuiwang},
title = {FlowX: Towards Explainable Graph Neural Networks via Message Flows},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2024},
volume = {46},
number = {7},
pages = {4567--4578},
doi = {10.1109/tpami.2023.3347470}
}
EUVIMED