T2G-FORMER: Organizing Tabular Features into Relation Graphs Promotes Heterogeneous Feature Interaction
Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (9) · 10720-10728
DOI: 10.1609/aaai.v37i9.26272 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Jiahuan Yan und 4 weiteren Autor:innen. Die Arbeit wurde bisher 41-mal zitiert (Crossref).
Abstract (Originalsprache)
Recent development of deep neural networks (DNNs) for tabular learning has largely benefited from the capability of DNNs for automatic feature interaction. However, the heterogeneity nature of tabular features makes such features relatively independent, and developing effective methods to promote tabular feature interaction still remains an open problem. In this paper, we propose a novel Graph Estimator, which automatically estimates the relations among tabular features and builds graphs by assigning edges between related features. Such relation graphs organize independent tabular features into a kind of graph data such that interaction of nodes (tabular features) can be conducted in an orderly fashion. Based on our proposed Graph Estimator, we present a bespoke Transformer network tailored for tabular learning, called T2G-Former, which processes tabular data by performing tabular feature interaction guided by the relation graphs. A specific Cross-level Readout collects salient features predicted by the layers in T2G-Former across different levels, and attains global semantics for final prediction. Comprehensive experiments show that our T2G-Former achieves superior performance among DNNs and is competitive with non-deep Gradient Boosted Decision Tree models. The code and detailed results are available at https://github.com/jyansir/t2g-former.
Zitieren
APA
Yan, J., Chen, J., Wu, Y., Chen, D. Z., & Wu, J. (2023). T2G-FORMER: Organizing Tabular Features into Relation Graphs Promotes Heterogeneous Feature Interaction. Proceedings of the AAAI Conference on Artificial Intelligence, 37(9), 10720-10728. https://doi.org/10.1609/aaai.v37i9.26272
Vancouver
Yan J, Chen J, Wu Y, Chen DZ, Wu J. T2G-FORMER: Organizing Tabular Features into Relation Graphs Promotes Heterogeneous Feature Interaction. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(9):10720-10728. doi:10.1609/aaai.v37i9.26272
BibTeX
@article{Yan2023,
author = {Yan, Jiahuan and Chen, Jintai and Wu, Yixuan and Chen, Danny Z. and Wu, Jian},
title = {T2G-FORMER: Organizing Tabular Features into Relation Graphs Promotes Heterogeneous Feature Interaction},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2023},
volume = {37},
number = {9},
pages = {10720--10728},
doi = {10.1609/aaai.v37i9.26272}
}
EUVIMED