Skip to content

cpb-cbb/TabNSA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

TabNSA

This is the repository code for "TabNSA: Native Sparse Attention for Efficient Tabular Data Learning".

📄 Paper: TabNSA: Native Sparse Attention for Efficient Tabular Data Learning

Overview

TabNSA introduces a native sparse attention mechanism tailored for tabular data. It achieves superior performance and accuracy on multiple benchmark datasets compared to existing models.

Highlights

  • Native sparse attention architecture for tabular inputs
  • Significantly improved classification/regression performance
  • Competitive results on standard tabular benchmarks
  • Easily pluggable into PyTorch training pipelines

Installation

git clone https://github.com/yourusername/TabNSA.git
cd TabNSA
pip install -r requirements.txt

About

use for llmTDM

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages