Data Heterogeneity Modeling for Trustworthy Machine Learning

TL;DR

This paper surveys heterogeneity-aware machine learning, emphasizing the importance of modeling data diversity throughout the ML pipeline to improve robustness, fairness, and reliability across various critical fields.

Contribution

It provides a comprehensive overview of heterogeneity-aware ML, highlighting its benefits, applications, and future research directions in addressing data diversity challenges.

Findings

Heterogeneity-aware ML enhances model robustness and fairness.

Applying heterogeneity considerations improves generalization across domains.

The survey identifies key future research opportunities in heterogeneity modeling.

Abstract

Data heterogeneity plays a pivotal role in determining the performance of machine learning (ML) systems. Traditional algorithms, which are typically designed to optimize average performance, often overlook the intrinsic diversity within datasets. This oversight can lead to a myriad of issues, including unreliable decision-making, inadequate generalization across different domains, unfair outcomes, and false scientific inferences. Hence, a nuanced approach to modeling data heterogeneity is essential for the development of dependable, data-driven systems. In this survey paper, we present a thorough exploration of heterogeneity-aware machine learning, a paradigm that systematically integrates considerations of data heterogeneity throughout the entire ML pipeline -- from data collection and model training to model evaluation and deployment. By applying this approach to a variety of critical fields, including healthcare, agriculture, finance, and recommendation systems, we demonstrate the substantial benefits and potential of heterogeneity-aware ML. These applications underscore how a deeper understanding of data diversity can enhance model robustness, fairness, and reliability and help model diagnosis and improvements. Moreover, we delve into future directions and provide research opportunities for the whole data mining community, aiming to promote the development of heterogeneity-aware ML.