A Layered Aggregate Engine for Analytics Workloads
This paper showed that the theory developed above, when combined with novel engineering techniques, can be used to build an effective prototype inDB ML system.
Authors: Maximilian Schleich, Dan Olteanu, Mahmoud Abo Khamis, Hung Q. Ngo, XuanLong Nguyen. 2019.
In Proceedings of the 2019 International Conference on Management of Data (SIGMOD ‘19).
This paper introduces LMFAO (Layered Multiple Functional Aggregate Optimization), an in-memory optimization and execution engine for batches of aggregates over the input database. The primary motivation for this work stems from the observation that for a variety of analytics over databases, their data-intensive tasks can be decomposed into group-by aggregates over the join of the input database relations. We exemplify the versatility and competitiveness of LMFAO for a handful of widely used analytics: learning ridge linear regression, classication trees, regression trees, and the structure of Bayesian networks using Chow-Liu trees; and data cubes used for exploration in data warehousing.
Read the PDF: A Layered Aggregate Engine for Analytics Workloads