A Declarative Query Language for Scientific Machine Learning

TL;DR

The paper introduces MQL, a declarative query language designed to democratize machine learning for scientists without deep technical expertise, demonstrated through materials science applications.

Contribution

It proposes MQL, a new high-level language for machine learning, enabling easier access and use for non-expert users, with implementation insights and practical experiments.

Findings

MQL simplifies machine learning workflows for non-experts.

Implementation over relational databases is feasible.

Successful application in materials science workflows.

Abstract

The popularity of data science as a discipline and its importance in the emerging economy and industrial progress dictate that machine learning be democratized for the masses. This also means that the current practice of workforce training using machine learning tools, which requires low-level statistical and algorithmic details, is a barrier that needs to be addressed. Similar to data management languages such as SQL, machine learning needs to be practiced at a conceptual level to help make it a staple tool for general users. In particular, the technical sophistication demanded by existing machine learning frameworks is prohibitive for many scientists who are not computationally savvy or well versed in machine learning techniques. The learning curve to use the needed machine learning tools is also too high for them to take advantage of these powerful platforms to rapidly advance science. In this paper, we introduce a new declarative machine learning query language, called {\em MQL}, for naive users. We discuss its merit and possible ways of implementing it over a traditional relational database system. We discuss two materials science experiments implemented using MQL on a materials science workflow system called MatFlow.