Rkmeans: Fast Clustering for Relational Data
[edit]
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, PMLR 108:27422752, 2020.
Abstract
Conventional machine learning algorithms cannot be applied until a data matrix is available to process. When the data matrix needs to be obtained from a relational database via a feature extraction query, the computation cost can be prohibitive, as the data matrix may be (much) larger than the total input relation size. This paper introduces Rkmeans, or relational kmeans algorithm, for clustering relational data tuples without having to access the full data matrix. As such, we avoid having to run the expensive feature extraction query and storing its output. Our algorithm leverages the underlying structures in relational data. It involves construction of a small grid coreset of the data matrix for subsequent cluster construction. This gives a constant approximation for the kmeans objective, while having asymptotic runtime improvements over standard approaches of first running the database query and then clustering. Empirical results show ordersofmagnitude speedup, and Rkmeans can run faster on the database than even just computing the data matrix.
Related Material


