@article{KunftKatsifodimosSchelteretal.2019,
  author    = {Kunft, Andreas and Katsifodimos, Asterios and Schelter, Sebastian and Bress, Sebastian and Rabl, Tilmann and Markl, Volker},
  title     = {An Intermediate Representation for Optimizing Machine Learning Pipelines},
  series = {Proceedings of the VLDB Endowment},
  volume    = {12},
  journal   = {Proceedings of the VLDB Endowment},
  number    = {11},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {2150-8097},
  doi       = {10.14778/3342263.3342633},
  pages     = {1553 -- 1567},
  year      = {2019},
  abstract  = {Machine learning (ML) pipelines for model training and validation typically include preprocessing, such as data cleaning and feature engineering, prior to training an ML model. Preprocessing combines relational algebra and user-defined functions (UDFs), while model training uses iterations and linear algebra. Current systems are tailored to either of the two. As a consequence, preprocessing and ML steps are optimized in isolation. To enable holistic optimization of ML training pipelines, we present Lara, a declarative domain-specific language for collections and matrices. Lara's inter-mediate representation (IR) reflects on the complete program, i.e., UDFs, control flow, and both data types. Two views on the IR enable diverse optimizations. Monads enable operator pushdown and fusion across type and loop boundaries. Combinators provide the semantics of domain-specific operators and optimize data access and cross-validation of ML algorithms. Our experiments on preprocessing pipelines and selected ML algorithms show the effects of our proposed optimizations on dense and sparse data, which achieve speedups of up to an order of magnitude.},
  language  = {en}
}