Quishi Bai: Maliva: Using Machine Learning to Rewrite Visualization Queries Under Time Constraints

As a powerful way for people to gain insights from data quickly and intuitively,  visualization is becoming increasingly important in the Big Data era. Considering data-visualization systems where a middleware layer translates a frontend request to a SQL query to a backend database to compute visual results.  In this talk, we study the problem of answering a visualization request within a limited time due to the responsiveness requirement.  We propose a novel middleware solution called Maliva based on machine learning (ML) techniques.  Maliva applies the Markov Decision Process (MDP) model to decide how to rewrite queries and uses instances to train an agent to make a sequence of decisions judiciously for an online request.  Our experiments on both real and synthetic datasets show that Maliva performs significantly better than a baseline solution that does not do any rewriting, in terms of both the probability of serving requests interactively and query execution time.

Qiushi Bai is a Ph.D. candidate in the Computer Science Department at UC Irvine. He received his Master’s and Bachelor’s degrees in CS from Northeastern University in China. His research interests have focused on improving query performance for big data analytics and visualizations.