ts3l - v0.70

New Feature

• Introduced TabularBinning

- Python
Published by Alcoholrithm 12 months ago

ts3l - v0.60

New Features

• Support modular designs for embedding and backbone module. The currently supported modules are:
  • Embedding modules: identity feature_tokenizer (from Revisiting Deep Learning Models for Tabular Data)
  • Backbone modules: mlp transformer

Enhancements

• Split reconstruction head for DAE and VIME: Implement separate reconstruction heads for categorical and continuous features, enhancing the handling of heterogeneous data.

- Python
Published by Alcoholrithm about 1 year ago

ts3l - v0.50

1. Module Optimization Enhanced performance by optimizing several modules, resulting in more efficient and faster execution.

2. Refactored Forward and Loss Calculation Logic Moved the forward and loss calculation logic from Lightning modules to functional modules. This change improves modularity and maintainability of the codebase.

3. Code Refactoring Refactored the overall codebase for better readability, and maintainability.

4. New Freeze Encoder Flag Added a freezeencoder flag to the setsecond_phase method. This flag allows users to easily freeze or unfreeze the encoder during the second phase of training, providing greater flexibility in model training.

- Python
Published by Alcoholrithm over 1 year ago

ts3l - v0.41

Bug Fix

Removed unnecessary print statements

- Python
Published by Alcoholrithm almost 2 years ago

ts3l - v0.40

1. Release SwitchTab
2. Add the weight initialization when initializing the model

- Python
Published by Alcoholrithm almost 2 years ago

ts3l - v0.30

Release Denoising AutoEncoder (DAE).

- Python
Published by Alcoholrithm almost 2 years ago

ts3l - v0.21

Incorporate data_hparams into Config

- Python
Published by Alcoholrithm almost 2 years ago

ts3l - v0.20

Release Lightning Modules for VIME, SubTab, and SCARF.

- Python
Published by Alcoholrithm almost 2 years ago

ts3l - v0.10

Release of nn.Module Implementations for VIME, SubTab, and SCARF, Including Their Corresponding Datasets

- Python
Published by Alcoholrithm almost 2 years ago