EUVIMEDEUVIMED entdecken
Crossref

SwitchTab: Switched Autoencoders Are Effective Tabular Learners

Jing Wu, Suiyao Chen, Qi Zhao, Renat Sergazinov, Chen Li, Shengjie Liu, Chongchao Zhao, Tianpei Xie, Hanqing Guo, Cheng Ji, Daniel Cociorva, Hakan Brunzell

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (14) · 15924-15933

DOI: 10.1609/aaai.v38i14.29523 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Jing Wu und 11 weiteren Autor:innen. Die Arbeit wurde bisher 28-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Self-supervised representation learning methods have achieved significant success in computer vision and natural language processing (NLP), where data samples exhibit explicit spatial or semantic dependencies. However, applying these methods to tabular data is challenging due to the less pronounced dependencies among data samples. In this paper, we address this limitation by introducing SwitchTab, a novel self-supervised method specifically designed to capture latent dependencies in tabular data. SwitchTab leverages an asymmetric encoder-decoder framework to decouple mutual and salient features among data pairs, resulting in more representative embeddings. These embeddings, in turn, contribute to better decision boundaries and lead to improved results in downstream tasks. To validate the effectiveness of SwitchTab, we conduct extensive experiments across various domains involving tabular data. The results showcase superior performance in end-to-end prediction tasks with fine-tuning. Moreover, we demonstrate that pre-trained salient embeddings can be utilized as plug-and-play features to enhance the performance of various traditional classification methods (e.g., Logistic Regression, XGBoost, etc.). Lastly, we highlight the capability of SwitchTab to create explainable representations through visualization of decoupled mutual and salient features in the latent space.

Zitieren

APA

Wu, J., Chen, S., Zhao, Q., Sergazinov, R., Li, C., Liu, S., Zhao, C., Xie, T., Guo, H., Ji, C., Cociorva, D., & Brunzell, H. (2024). SwitchTab: Switched Autoencoders Are Effective Tabular Learners. Proceedings of the AAAI Conference on Artificial Intelligence, 38(14), 15924-15933. https://doi.org/10.1609/aaai.v38i14.29523

Vancouver

Wu J, Chen S, Zhao Q, Sergazinov R, Li C, Liu S, et al. SwitchTab: Switched Autoencoders Are Effective Tabular Learners. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(14):15924-15933. doi:10.1609/aaai.v38i14.29523

BibTeX
@article{Wu2024,
  author = {Wu, Jing and Chen, Suiyao and Zhao, Qi and Sergazinov, Renat and Li, Chen and Liu, Shengjie and Zhao, Chongchao and Xie, Tianpei and Guo, Hanqing and Ji, Cheng and Cociorva, Daniel and Brunzell, Hakan},
  title = {SwitchTab: Switched Autoencoders Are Effective Tabular Learners},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {14},
  pages = {15924--15933},
  doi = {10.1609/aaai.v38i14.29523}
}
Kostenlos starten →