DiffML: End-to-end Differentiable ML Pipelines
This work addresses the challenge of automating and optimizing entire ML pipelines for practitioners, though it is incremental as it builds on existing differentiable programming concepts.
The paper tackles the problem of automating ML pipeline construction by proposing DiffML, a framework for end-to-end differentiable pipelines that jointly trains both the model and preprocessing steps like data cleaning and feature selection using backpropagation, demonstrating initial feasibility through differentiable formulations of these steps.
In this paper, we present our vision of differentiable ML pipelines called DiffML to automate the construction of ML pipelines in an end-to-end fashion. The idea is that DiffML allows to jointly train not just the ML model itself but also the entire pipeline including data preprocessing steps, e.g., data cleaning, feature selection, etc. Our core idea is to formulate all pipeline steps in a differentiable way such that the entire pipeline can be trained using backpropagation. However, this is a non-trivial problem and opens up many new research questions. To show the feasibility of this direction, we demonstrate initial ideas and a general principle of how typical preprocessing steps such as data cleaning, feature selection and dataset selection can be formulated as differentiable programs and jointly learned with the ML model. Moreover, we discuss a research roadmap and core challenges that have to be systematically tackled to enable fully differentiable ML pipelines.