TabMixer: Advancing Tabular Data Analysis with an Enhanced MLP-Mixer Approach

Welcome to the repository for "TabMixer: Advancing Tabular Data Analysis with an Enhanced MLP-Mixer Approach".

Paper Acceptance 🎉: This work has been accepted for publication in Journal of Pattern Analysis and Applications.

Requirements

Prerequisites

To run this code, ensure that you have:

• Python 3.9.18 installed on your system.

Installation

1. Clone this repository:

   git clone https://github.com/aseslamian/TabMixer
   cd TabMixer

2. Install the required packages:

   pip install -r requirements.txt

---

Running the Code

Supervised Learning

Run the following command to execute the supervised learning approach:

python supervised.py

Transfer Learning

Run the following command to execute the transfer learning approach:

python Transfer_learning.py

Feature Incremental Learning

Run the following command to execute the feature incremental learning approach:

python Feature_incremental.py

---

Examples

You can find example datasets and usage scenarios in the Example folder. These examples provide step-by-step instructions on how to use the code effectively.

---

Citation

If you use this code or reference our study in your work, please cite:

@article{eslamian2025tabmixer,
  title={TabMixer: advancing tabular data analysis with an enhanced MLP-mixer approach},
  author={Eslamian, Ali and Cheng, Qiang},
  journal={Pattern Analysis and Applications},
  volume={28},
  number={2},
  pages={1--17},
  year={2025},
  publisher={Springer}
}

This work draws inspiration from Transtab by RyanWangZf, and some parts of the implementation have been adapted from this repository.