rtdl
MTR
rtdl | MTR | |
---|---|---|
2 | 1 | |
726 | 9 | |
- | - | |
0.0 | 4.9 | |
6 months ago | 8 months ago | |
Python | Python | |
Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
rtdl
-
[R] New paper on Tabular DL: "On Embeddings for Numerical Features in Tabular Deep Learning"
JFYI: recently, we have split our codebase into separate projects: - https://github.com/Yura52/rtdl - https://github.com/Yura52/tabular-dl-revisiting-models - (the new one) https://github.com/Yura52/tabular-dl-num-embeddings
MTR
-
Rethinking Data Augmentation for Tabular Data in Deep Learning
Tabular data is the most widely used data format in machine learning (ML). While tree-based methods outperform DL-based methods in supervised learning, recent literature reports that self-supervised learning with Transformer-based models outperforms tree-based methods. In the existing literature on self-supervised learning for tabular data, contrastive learning is the predominant method. In contrastive learning, data augmentation is important to generate different views. However, data augmentation for tabular data has been difficult due to the unique structure and high complexity of tabular data. In addition, three main components are proposed together in existing methods: model structure, self-supervised learning methods, and data augmentation. Therefore, previous works have compared the performance without comprehensively considering these components, and it is not clear how each component affects the actual performance. In this study, we focus on data augmentation to address these issues. We propose a novel data augmentation method, $\textbf{M}$ask $\textbf{T}$oken $\textbf{R}$eplacement ($\texttt{MTR}$), which replaces the mask token with a portion of each tokenized column; $\texttt{MTR}$ takes advantage of the properties of Transformer, which is becoming the predominant DL-based architecture for tabular data, to perform data augmentation for each column embedding. Through experiments with 13 diverse public datasets in both supervised and self-supervised learning scenarios, we show that $\texttt{MTR}$ achieves competitive performance against existing data augmentation methods and improves model performance. In addition, we discuss specific scenarios in which $\texttt{MTR}$ is most effective and identify the scope of its application. The code is available at https://github.com/somaonishi/MTR/.
What are some alternatives?
quickai - QuickAI is a Python library that makes it extremely easy to experiment with state-of-the-art Machine Learning models.
Papers-in-100-Lines-of-Code - Implementation of papers in 100 lines of code.
PyGame-Learning-Environment - PyGame Learning Environment (PLE) -- Reinforcement Learning Environment in Python.
rtdl - Research on Tabular Deep Learning (Python package & papers) [Moved to: https://github.com/Yura52/rtdl]
aimm - AI Model Manager: Install a model once, and use everywhere 🤩 Users could save huge amounts of disk space 💽 For developers, less code to manage of downloading and installing models 👩🏽💻 aimodels.json is used like requirements.txt / package.json! 📝
tabular-dl-pretrain-objectives - Revisiting Pretrarining Objectives for Tabular Deep Learning
neuroaid - :zap: :books: Papers and other material for getting started with Neuro-AI! :brain: :boom:
thesis - MSc thesis on: Classifying brain activity using EEG and automated time tracking of computer use (using ActivityWatch)
tabular-dl-tabr - The implementation of "TabR: Unlocking the Power of Retrieval-Augmented Tabular Deep Learning"
rtdl-num-embeddings - (NeurIPS 2022) On Embeddings for Numerical Features in Tabular Deep Learning
papers-with-data - A curated list of papers that released datasets along with their work
tcow - Tracking through Containers and Occluders in the Wild (CVPR 2023) - Official Implementation