TFWT: Tabular Feature Weighting with Transformer

Authors: Xinhao Zhang, Zaitian Wang, Lu Jiang, Wanfu Gao, Pengfei Wang, Kunpeng Liu

IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our extensive experimental results across various real-world datasets and diverse downstream tasks show the effectiveness of TFWT and highlight the potential for enhancing feature weighting in tabular data analysis.
Researcher Affiliation Academia 1Portland State University 2Computer Network Information Center, Chinese Academy of Sciences 3University of Chinese Academy of Sciences, Chinese Academy of Sciences 4Dalian Maritime University 5Jilin University
Pseudocode Yes Algorithm 1: Training of TFWT
Open Source Code No The paper does not contain any statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets Yes We evaluate the proposed method with four real-world datasets: Amazon Commerce Reviews Set (AM) [Liu, 2011] from UCI... Online Shoppers Purchasing Intention Dataset (OS) [Sakar and Kastro, 2018] from UCI... MAGIC Gamma Telescope Dataset (MA) [Bock, 2007] from UCI... Smoking and Drinking Dataset with body signal (SD) [Her, 2023] from Kaggle...
Dataset Splits No For each dataset, we randomly selected between 60% and 80% as training data. The paper mentions training data but does not specify the percentage or absolute number of samples used for a dedicated validation set.
Hardware Specification Yes The models were trained on NVIDIA A100.
Software Dependencies No We implemented TFWT using Py Torch and Scikit-learn. The paper lists software used but does not provide specific version numbers for PyTorch or Scikit-learn.
Experiment Setup Yes The initial learning rate was set between 10^-3 and 10^-5. For model regularization, the dropout rate was fixed at 0.2.