A Unified Transferable Model for ML-Enhanced DBMS

TL;DR

This paper introduces MTMLF, a unified transfer learning model for ML-enhanced DBMS that captures transferable knowledge across tasks and databases, improving efficiency and adaptability in cloud database services.

Contribution

The paper presents a novel multi-task and pre-train fine-tune framework that enables transferability across DBMS tasks and databases, addressing limitations of existing ML-based solutions.

Findings

Effective transfer of knowledge across tasks and databases.

Reduces retraining and data requirements for new DBs.

Demonstrates promising results in query optimization.

Abstract

Recently, the database management system (DBMS) community has witnessed the power of machine learning (ML) solutions for DBMS tasks. Despite their promising performance, these existing solutions can hardly be considered satisfactory. First, these ML-based methods in DBMS are not effective enough because they are optimized on each specific task, and cannot explore or understand the intrinsic connections between tasks. Second, the training process has serious limitations that hinder their practicality, because they need to retrain the entire model from scratch for a new DB. Moreover, for each retraining, they require an excessive amount of training data, which is very expensive to acquire and unavailable for a new DB. We propose to explore the transferabilities of the ML methods both across tasks and across DBs to tackle these fundamental drawbacks. In this paper, we propose a unified model MTMLF that uses a multi-task training procedure to capture the transferable knowledge across tasks and a pre-train fine-tune procedure to distill the transferable meta knowledge across DBs. We believe this paradigm is more suitable for cloud DB service, and has the potential to revolutionize the way how ML is used in DBMS. Furthermore, to demonstrate the predicting power and viability of MTMLF, we provide a concrete and very promising case study on query optimization tasks. Last but not least, we discuss several concrete research opportunities along this line of work.