TY - GEN
T1 - Interpretable Graph Neural Networks for Tabular Data
AU - Alkhatib, Amr
AU - Ennadir, Sofiane
AU - Boström, Henrik
AU - Vazirgiannis, Michalis
N1 - Publisher Copyright:
© 2024 The Authors.
PY - 2024/10/16
Y1 - 2024/10/16
N2 - Data in tabular format is frequently occurring in real-world applications.Graph Neural Networks (GNNs) have recently been extended to effectively handle such data, allowing feature interactions to be captured through representation learning.However, these approaches essentially produce black-box models, in the form of deep neural networks, precluding users from following the logic behind the model predictions.We propose an approach, called IGNNet (Interpretable Graph Neural Network for tabular data), which constrains the learning algorithm to produce an interpretable model, where the model shows how the predictions are exactly computed from the original input features.A large-scale empirical investigation is presented, showing that IGNNet is performing on par with state-ofthe-art machine-learning algorithms that target tabular data, including XGBoost, Random Forests, and TabNet.At the same time, the results show that the explanations obtained from IGNNet are aligned with the true Shapley values of the features without incurring any additional computational overhead.
AB - Data in tabular format is frequently occurring in real-world applications.Graph Neural Networks (GNNs) have recently been extended to effectively handle such data, allowing feature interactions to be captured through representation learning.However, these approaches essentially produce black-box models, in the form of deep neural networks, precluding users from following the logic behind the model predictions.We propose an approach, called IGNNet (Interpretable Graph Neural Network for tabular data), which constrains the learning algorithm to produce an interpretable model, where the model shows how the predictions are exactly computed from the original input features.A large-scale empirical investigation is presented, showing that IGNNet is performing on par with state-ofthe-art machine-learning algorithms that target tabular data, including XGBoost, Random Forests, and TabNet.At the same time, the results show that the explanations obtained from IGNNet are aligned with the true Shapley values of the features without incurring any additional computational overhead.
U2 - 10.3233/FAIA240697
DO - 10.3233/FAIA240697
M3 - Conference contribution
AN - SCOPUS:85213390603
T3 - Frontiers in Artificial Intelligence and Applications
SP - 1848
EP - 1855
BT - ECAI 2024 - 27th European Conference on Artificial Intelligence, Including 13th Conference on Prestigious Applications of Intelligent Systems, PAIS 2024, Proceedings
A2 - Endriss, Ulle
A2 - Melo, Francisco S.
A2 - Bach, Kerstin
A2 - Bugarin-Diz, Alberto
A2 - Alonso-Moral, Jose M.
A2 - Barro, Senen
A2 - Heintz, Fredrik
PB - IOS Press BV
T2 - 27th European Conference on Artificial Intelligence, ECAI 2024
Y2 - 19 October 2024 through 24 October 2024
ER -