Standard
Logical Distillation of Graph Neural Networks. / Pluska, Alexander
; Welke, Pascal; Gärtner, Thomas et al.
Proceedings of the 21st International Conference on Principles of Knowledge Representation and Reasoning. ed. / Pierre Marquis; Magdalena Ortiz; Maurice Pagnucco. IJCAI, 2024. p. 920-930.
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Chapter
Harvard
Pluska, A
, Welke, P, Gärtner, T & Malhotra, S 2024,
Logical Distillation of Graph Neural Networks. in P Marquis, M Ortiz & M Pagnucco (eds),
Proceedings of the 21st International Conference on Principles of Knowledge Representation and Reasoning. IJCAI, pp. 920-930.
https://doi.org/10.24963/KR.2024/86APA
Pluska, A.
, Welke, P., Gärtner, T., & Malhotra, S. (2024).
Logical Distillation of Graph Neural Networks. In P. Marquis, M. Ortiz, & M. Pagnucco (Eds.),
Proceedings of the 21st International Conference on Principles of Knowledge Representation and Reasoning (pp. 920-930). IJCAI.
https://doi.org/10.24963/KR.2024/86Vancouver
Pluska A
, Welke P, Gärtner T, Malhotra S.
Logical Distillation of Graph Neural Networks. In Marquis P, Ortiz M, Pagnucco M, editors, Proceedings of the 21st International Conference on Principles of Knowledge Representation and Reasoning. IJCAI. 2024. p. 920-930 doi: 10.24963/KR.2024/86
Author
Pluska, Alexander
; Welke, Pascal ; Gärtner, Thomas et al. /
Logical Distillation of Graph Neural Networks. Proceedings of the 21st International Conference on Principles of Knowledge Representation and Reasoning. editor / Pierre Marquis ; Magdalena Ortiz ; Maurice Pagnucco. IJCAI, 2024. pp. 920-930
Bibtex
@inbook{f0ea5c13a128402b8867e38b2849ffab,
title = "Logical Distillation of Graph Neural Networks",
abstract = "We present a logic based interpretable model for learning on graphs and an algorithm to distill this model from a Graph Neural Network (GNN). Recent results have shown connections between the expressivity of GNNs and the two-variable fragment of first-order logic with counting quantifiers (C2). We introduce a decision-tree based model which leverages an extension of C2 to distill interpretable logical classifiers from GNNs. We test our approach on multiple GNN architectures. The distilled models are interpretable, succinct, and attain similar accuracy to the underlying GNN. Furthermore, when the ground truth is expressible in C2, our approach outperforms the GNN.",
author = "Alexander Pluska and Pascal Welke and Thomas G{\"a}rtner and Sagar Malhotra",
year = "2024",
month = nov,
day = "2",
doi = "10.24963/KR.2024/86",
language = "English",
pages = "920--930",
editor = "Pierre Marquis and Magdalena Ortiz and Maurice Pagnucco",
booktitle = "Proceedings of the 21st International Conference on Principles of Knowledge Representation and Reasoning",
publisher = "IJCAI",
}
RIS
TY - CHAP
T1 - Logical Distillation of Graph Neural Networks
AU - Pluska, Alexander
AU - Welke, Pascal
AU - Gärtner, Thomas
AU - Malhotra, Sagar
PY - 2024/11/2
Y1 - 2024/11/2
N2 - We present a logic based interpretable model for learning on graphs and an algorithm to distill this model from a Graph Neural Network (GNN). Recent results have shown connections between the expressivity of GNNs and the two-variable fragment of first-order logic with counting quantifiers (C2). We introduce a decision-tree based model which leverages an extension of C2 to distill interpretable logical classifiers from GNNs. We test our approach on multiple GNN architectures. The distilled models are interpretable, succinct, and attain similar accuracy to the underlying GNN. Furthermore, when the ground truth is expressible in C2, our approach outperforms the GNN.
AB - We present a logic based interpretable model for learning on graphs and an algorithm to distill this model from a Graph Neural Network (GNN). Recent results have shown connections between the expressivity of GNNs and the two-variable fragment of first-order logic with counting quantifiers (C2). We introduce a decision-tree based model which leverages an extension of C2 to distill interpretable logical classifiers from GNNs. We test our approach on multiple GNN architectures. The distilled models are interpretable, succinct, and attain similar accuracy to the underlying GNN. Furthermore, when the ground truth is expressible in C2, our approach outperforms the GNN.
U2 - 10.24963/KR.2024/86
DO - 10.24963/KR.2024/86
M3 - Chapter
SP - 920
EP - 930
BT - Proceedings of the 21st International Conference on Principles of Knowledge Representation and Reasoning
A2 - Marquis, Pierre
A2 - Ortiz, Magdalena
A2 - Pagnucco, Maurice
PB - IJCAI
ER -
