What's Changed in v1.3.0
This Release includes several changes to the mambular
package, focusing on refactoring imports and enhancing the functionality of the BaseModel
and TaskModel
classes. The most important changes include moving BaseModel
and TaskModel
to a new utils
directory, updating import paths accordingly, and adding new methods for pretraining embeddings. Additionally, two new models, Trompt and AutoInt are included in v1.3.0
Refactoring imports:
- Moved
BaseModel
andTaskModel
tomambular/base_models/utils/
and updated import paths in all relevant files. [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13]
Include new models
- New model architectures
Trompt
andAutoInt
are now included into mambular.
Introduce pretraining
option:
- Added pertaining functionality for all models that use encoders.
Include dilation to 1DConv layers in Mambular/TabulaRNN
- See Issue #182
Enhancements to BaseModel
:
- Added new methods for embedding management, including
embedding_parameters
,encode_features
,get_embedding_state_dict
, andload_embedding_state_dict
. - Modified the
encode
method to support gradient computation and shuffling embeddings.
Enhancements to TaskModel
:
- Added a new method
pretrain_embeddings
for pretraining embeddings using contrastive learning. - Introduced helper methods
get_knn
andcontrastive_loss
to support the new pretraining functionality.
Miscellaneous changes:
- Added print statements for debugging and logging purposes. [1] [2]
- Minor formatting changes for code readability.