yandex-research/rtdl-revisiting-models

(NeurIPS 2021) Revisiting Deep Learning Models for Tabular Data

47
/ 100
Emerging

This project helps data scientists and machine learning practitioners evaluate and choose the best deep learning models for problems involving structured, tabular data. It provides tools to input your datasets and test how different neural network architectures perform, giving you insights into which models are strong baselines and which offer state-of-the-art performance for your specific data challenges. The primary users are data scientists who work with machine learning on real-world datasets.

324 stars. No commits in the last 6 months.

Use this if you are a data scientist looking to apply advanced deep learning techniques to tabular data problems and want to understand which models (like MLPs, ResNets, or FT-Transformers) offer the best performance and when.

Not ideal if you are exclusively working with gradient-boosted decision trees (GBDTs) and are not interested in exploring deep learning alternatives for tabular data.

data-science machine-learning tabular-data predictive-modeling deep-learning-evaluation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

324

Forks

58

Language

Python

License

Apache-2.0

Last pushed

Nov 12, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yandex-research/rtdl-revisiting-models"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.