yandex-research/rtdl

Stars
874
Rank 52,219 (Top 2 %)
Language
Python
License
Apache License 2.0
Created over 3 years ago
Updated 4 months ago

yandex-research/rtdl

yandex-research

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Research on Tabular Deep Learning: Papers & Packages

Research on Tabular Deep Learning

For paper implementations, see the section "Papers and projects".

rtdl is a PyTorch-based package providing a user-friendly API for the main models and concepts from our papers. See the documentation.

Press "Watch" to stay up to date with new papers and releases!

Feel free to report issues and post questions/feedback/ideas.

Papers and projects

Name	Location	Comment
Revisiting Pretraining Objectives for Tabular Deep Learning	link	arXiv 2022
On Embeddings for Numerical Features in Tabular Deep Learning	link	arXiv 2022
Revisiting Deep Learning Models for Tabular Data	link	NeurIPS 2021
`rtdl`	link	Python package

ddpm-segmentation

Label-Efficient Semantic Segmentation with Diffusion Models (ICLR'2022)

tab-ddpm

[ICML 2023] The official implementation of the paper "TabDDPM: Modelling Tabular Data with Diffusion Models"

rtdl-num-embeddings

(NeurIPS 2022) On Embeddings for Numerical Features in Tabular Deep Learning

navigan

Navigating the GAN Parameter Space for Semantic Image Editing

Jupyter Notebook

tabular-dl-tabr

The implementation of "TabR: Unlocking the Power of Retrieval-Augmented Tabular Deep Learning"

rtdl-revisiting-models

(NeurIPS 2021) Revisiting Deep Learning Models for Tabular Data

swarm

Official code for "SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient"

DeDLOC

Official code for "Distributed Deep Learning in Open Collaborations" (NeurIPS 2021)

Jupyter Notebook

RuLeanALBERT

RuLeanALBERT is a pretrained masked language model for the Russian language that uses a memory-efficient architecture.

heterophilous-graphs

A Critical Look at the Evaluation of GNNs under Heterophily: Are We Really Making Progress?

invertible-cd

[NeurIPS'2024] Invertible Consistency Distillation for Text-Guided Image Editing in Around 7 Steps

GBDT-uncertainty

Jupyter Notebook

graph-glove

PyTorch code for the EMNLP 2020 paper "Embedding Words in Non-Vector Space with Unsupervised Graph Learning"

specexec

tabred

A Benchmark of Tabular Machine Learning in-the-Wild with real-world industry-grade tabular datasets

DVAR

Official implementation of "Is This Loss Informative? Faster Text-to-Image Customization by Tracking Objective Dynamics" (NeurIPS 2023)

sparqling-queries

This repo in the implementation of EMNLP'21 paper "SPARQLing Database Queries from Intermediate Question Decompositions" by Irina Saparina, Anton Osokin

moshpit-sgd

"Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices", official implementation

Jupyter Notebook

adaptive-diffusion

[CVPR'2024] Adaptive Teacher-Student Collaboration for Text-Conditional Diffusion Models

gan-transfer

Supplementary code for "When, Why, and Which Pretrained GANs Are Useful?" (ICLR'22)

Jupyter Notebook

vqdm

Official repository for VQDM:Accurate Compression of Text-to-Image Diffusion Models via Vector Quantization paper

btard

Code for the paper "Secure Distributed Training at Scale" (ICML 2022)

structural-graph-shifts

Evaluating Robustness and Uncertainty of Graph Models Under Structural Distributional Shifts (NeurIPS'23)

crosslingual_winograd

"It's All in the Heads" (Findings of ACL 2021), official implementation and data

gan_vs_diff_sr

Does Diffusion Beat GAN in Image Super Resolution?

distill-nf

Code for the paper: Distilling the Knowledge from Conditional Normalizing Flows

Jupyter Notebook

classification-measures

Official implementation and data for 'Good Classification Measures and How to Find Them' (NeurIPS 2021)

text-to-img-hypernymy

Official code for "Hypernymy Understanding Evaluation of Text-to-Image Models via WordNet Hierarchy"

Jupyter Notebook

tabm

TabM: Advancing Tabular Deep Learning With Parameter-Efficient Ensembling

dnar

The implementation of "Discrete Neural Algorithmic Reasoning"

learnable-init

Code for the paper: Discovering Weight Initializers with Meta-Learning

Jupyter Notebook

mind-your-format

Mind Your Format: Towards Consistent Evaluation of In-Context Learning Improvements

Jupyter Notebook

proxy-dirichlet-distillation

Implementation of "Scaling Ensemble Distribution Distillation to Many Classes with Proxy Targets" (NeurIPS 2021) and "Uncertainty Estimation in Autoregressive Structured Prediction" (ICLR 2021)

tabgraphs

A new benchmark of meaningful tabular datasets with known graph structure

msr

An official repository of "Multi-Sentence Resampling: A Simple Approach to Alleviate Dataset Length Bias and Beam-Search Degradation"