In order to show that data valuation is not limited to scikit-learn models, we should create a notebook demonstrating
the use of a PyTorch with one of the data valuation methods (e.g. TMCS). We could use Skorch to wrap the PyTorch model and then seamlessly use it with the existing data valuation code.
The purpose of this is two fold:
Document and show use of data valuation methods with non-scikit-learn models.
Test performance and behaviour of PyTorch models with Data Valuation's parallelization and serialization.
In order to show that data valuation is not limited to scikit-learn models, we should create a notebook demonstrating the use of a PyTorch with one of the data valuation methods (e.g. TMCS). We could use Skorch to wrap the PyTorch model and then seamlessly use it with the existing data valuation code.
The purpose of this is two fold:
This issue is related to #533