puhsu/tabular-dl-pretrain-objectives
Revisiting Pretrarining Objectives for Tabular Deep Learning
This project helps machine learning researchers and practitioners evaluate and reproduce state-of-the-art pretraining techniques for deep learning models on tabular data. It takes in various tabular datasets and configurations for deep learning models (like MLPs or Transformers), then applies different pretraining objectives, and outputs trained models and their performance metrics. It's designed for those exploring the effectiveness of pretraining strategies in tabular deep learning.
No commits in the last 6 months.
Use this if you are a machine learning researcher or practitioner interested in understanding and applying pretraining methods to improve deep learning models on structured, tabular datasets.
Not ideal if you are looking for a plug-and-play solution for general data analysis or a simple library for building traditional machine learning models on tabular data without deep learning pretraining.
Stars
67
Forks
11
Language
Python
License
—
Category
Last pushed
Aug 22, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/puhsu/tabular-dl-pretrain-objectives"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PriorLabs/TabPFN
⚡ TabPFN: Foundation Model for Tabular Data ⚡
pyg-team/pytorch-frame
Tabular Deep Learning Library for PyTorch
NVIDIA-Merlin/NVTabular
NVTabular is a feature engineering and preprocessing library for tabular data designed to...
PriorLabs/tabpfn-extensions
Community extensions for TabPFN - the foundation model for tabular data. Built with TabPFN! 🤗
pytorch-tabular/pytorch_tabular
A unified framework for Deep Learning Models on tabular data