Interpretable Automated Machine Learning in Maana(TM) Knowledge Platform

TL;DR

This paper presents Maana Meta-learning Service, an interpretable automated machine learning tool integrated into Maana Knowledge Platform, enabling guided pipeline search, hyper-parameter tuning, and knowledge generation for industrial applications.

Contribution

It introduces an interpretable, user-assisted autoML service with structured knowledge output, enhancing transparency and transferability in industrial machine learning workflows.

Findings

Validated on benchmark datasets showing effective pipeline search.

Generated structured knowledge aids inference and transfer to similar projects.

Enhances interpretability and user interaction in autoML processes.

Abstract

Machine learning is becoming an essential part of developing solutions for many industrial applications, but the lack of interpretability hinders wide industry adoption to rapidly build, test, deploy and validate machine learning models, in the sense that the insight of developing machine learning solutions are not structurally encoded, justified and transferred. In this paper we describe Maana Meta-learning Service, an interpretable and interactive automated machine learning service residing in Maana Knowledge Platform that performs machine-guided, user assisted pipeline search and hyper-parameter tuning and generates structured knowledge about decisions for pipeline profiling and selection. The service is shipped with Maana Knowledge Platform and is validated using benchmark dataset. Furthermore, its capability of deriving knowledge from pipeline search facilitates various inference tasks and transferring to similar data science projects.