AutoSmart: An Efficient and Automatic Machine Learning framework for Temporal Relational Data

TL;DR

AutoSmart is an end-to-end automated machine learning framework designed for temporal relational data, addressing data mining, resource control, and task generalization, and winning the 2019 KDD Cup AutoML track.

Contribution

It introduces a novel automatic framework that handles data processing, feature engineering, and model tuning for temporal relational data, with self-adjustable resource management.

Findings

Outperforms baseline solutions on multiple datasets

Successfully addresses key challenges in automating temporal relational data modeling

Wins the KDD Cup 2019 AutoML Track

Abstract

Temporal relational data, perhaps the most commonly used data type in industrial machine learning applications, needs labor-intensive feature engineering and data analyzing for giving precise model predictions. An automatic machine learning framework is needed to ease the manual efforts in fine-tuning the models so that the experts can focus more on other problems that really need humans' engagement such as problem definition, deployment, and business services. However, there are three main challenges for building automatic solutions for temporal relational data: 1) how to effectively and automatically mining useful information from the multiple tables and the relations from them? 2) how to be self-adjustable to control the time and memory consumption within a certain budget? and 3) how to give generic solutions to a wide range of tasks? In this work, we propose our solution that successfully addresses the above issues in an end-to-end automatic way. The proposed framework, AutoSmart, is the winning solution to the KDD Cup 2019 of the AutoML Track, which is one of the largest AutoML competition to date (860 teams with around 4,955 submissions). The framework includes automatic data processing, table merging, feature engineering, and model tuning, with a time\&memory controller for efficiently and automatically formulating the models. The proposed framework outperforms the baseline solution significantly on several datasets in various domains.