Neural Oblivious Decsion Ensembles #151
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This pull request introduces several significant changes to the
mambularproject, focusing on adding new modules, implementing utility functions, and simplifying the normalization layer selection in base models. The most important changes include the addition of the NODE model and the refactoring of normalization layer selection.New Modules and Functions:
mambular/arch_utils/data_aware_initialization.py: Added theModuleWithInitclass, which provides a base class for PyTorch modules with data-aware initialization on the first batch.mambular/arch_utils/layer_utils/sparsemax.py: Implemented the sparsemax function and its backward pass, providing a sparse alternative to softmax.mambular/arch_utils/node_utils.py: Introduced theODSTclass for differentiable decision tree models and theDenseBlockclass for stacking layers of decision trees.mambular/arch_utils/numpy_utils.py: Added thecheck_numpyfunction to ensure a tensor is converted to a NumPy array.Refactoring:
mambular/base_models/ft_transformer.py: Simplified the normalization layer selection by using theget_normalization_layerfunction. [1] [2]mambular/base_models/mlp.py: Refactored the normalization layer selection to use theget_normalization_layerfunction, reducing redundancy. [1] [2]