Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Methods and Opportunities at Small Scale (MOSS)

Efficient B-Tree Insertions Using Proximal Policy Optimization and Hierarchical Attention Models

Alexander Kastius · Nick Lechtenbörger · Felix Schulz · Johann Tast · Rainer Schlosser · Ralf Herbrich

Keywords: [ Databases ] [ B-Trees ] [ Optimization ] [ Reinforcement Learning ] [ Attention ]


Abstract:

B-trees are a fundamental component of any large database management system. They can grow to noticeable sizes, but their handling is non-trivial. We present a novel approach to use attention-based models with weight sharing across the hierarchical structure of the tree to parse such large trees fast and without the need for excessive training on large clusters. We present a use case in which the model is used in conjunction with PPO to manage write operations on such a tree.

Chat is not available.