RT info:eu-repo/semantics/article
T1 Graph Neural Network contextual embedding for Deep Learning on tabular data
A1 Villalaizán Vallelado, Mario
A1 Salvatori, Matteo
A1 Carro Martínez, Belén
A1 Sánchez Esguevillas, Antonio Javier
K1 Deep Learning
K1 Graph Neural Network
K1 Interaction Network
K1 Contextual embedding
K1 Tabular data
K1 Artificial Intelligence
AB All industries are trying to leverage Artificial Intelligence (AI) based on their existing big data which is available in so called tabular form, where each record is composed of a number of heterogeneous continuous and categorical columns also known as features. Deep Learning (DL) has constituted a major breakthrough for AI in fields related to human skills like natural language processing, but its applicability to tabular data has been more challenging. More classical Machine Learning (ML) models like tree-based ensemble ones usually perform better. This paper presents a novel DL model using Graph Neural Network (GNN) more specifically Interaction Network (IN), for contextual embedding and modeling interactions among tabular features. Its results outperform those of a recently published survey with DL benchmark based on seven public datasets, also achieving competitive results when compared to boosted-tree solutions.
PB Elsevier
SN 0893-6080
YR 2024
FD 2024
LK https://uvadoc.uva.es/handle/10324/72938
UL https://uvadoc.uva.es/handle/10324/72938
LA eng
NO Neural Networks, 2024, vol. 173, 106180
NO Producción Científica
DS UVaDOC
RD 24-dic-2024