Trompt: Towards a Better Deep Neural Network for Tabular Data

Kuan Yu Chen, Ping Han Chiang, Hsin Rung Chou, Ting Wei Chen, Darby Tien Hao Chang

研究成果: Conference article同行評審

摘要

Tabular data is arguably one of the most commonly used data structures in various practical domains, including finance, healthcare and e-commerce. However, based on a recently published tabular benchmark, we can see deep neural networks still fall behind tree-based models on tabular datasets (Grinsztajn et al., 2022). In this paper, we propose Trompt-which stands for Tabular Prompt-a novel architecture inspired by prompt learning of language models. The essence of prompt learning is to adjust a large pre-trained model through a set of prompts outside the model without directly modifying the model. Based on this idea, Trompt separates the learning strategy of tabular data into two parts for the intrinsic information of a table and the varied information among samples. Trompt is evaluated with the benchmark mentioned above. The experimental results demonstrate that Trompt outperforms state-of-the-art deep neural networks and is comparable to tree-based models (Figure 1).

原文English
頁(從 - 到)5036-5051
頁數16
期刊Proceedings of Machine Learning Research
202
出版狀態Published - 2023
事件40th International Conference on Machine Learning, ICML 2023 - Honolulu, United States
持續時間: 2023 7月 232023 7月 29

All Science Journal Classification (ASJC) codes

  • 人工智慧
  • 軟體
  • 控制與系統工程
  • 統計與概率

指紋

深入研究「Trompt: Towards a Better Deep Neural Network for Tabular Data」主題。共同形成了獨特的指紋。

引用此