“DiffML: End-to-end Differentiable ML Pipelines” was awarded as Best Paper Runner-Up at DEEM'23

The paper was written by Benjamin Hilprecht, Christian Hammacher, Eduardo Reis and Mohamed Abdelaal under the supervision of Carsten Binnig


The paper received the Best Paper Runner-Up Award at the 7th Workshop on Data Management for End-to-End Machine Learning (DEEM'23), hosted in conjunction with SIGMOD/PODS 2023.

Logo DEEM'23

In the paper, we demonstrate a research roadmap towards fully differentiable ML pipelines, and a general principle of how typical data engineering steps can be formulated as differentiable programs.

Learn more about the paper .