Visual Analytics For Machine Learning: A Data Perspective Survey

TL;DR

This survey reviews visualization techniques in machine learning from a data-centric perspective, categorizing data types, tasks, and analyzing trends to guide future research in interpretability and data quality improvement.

Contribution

It systematically organizes VIS4ML works focusing on data types and tasks, providing a comprehensive overview and identifying future research directions.

Findings

Six data-centric tasks identified across ML pipeline stages

Analysis of 143 papers reveals research distribution and trends

Future research directions in data quality and visualization for ML

Abstract

The past decade has witnessed a plethora of works that leverage the power of visualization (VIS) to interpret machine learning (ML) models. The corresponding research topic, VIS4ML, keeps growing at a fast pace. To better organize the enormous works and shed light on the developing trend of VIS4ML, we provide a systematic review of these works through this survey. Since data quality greatly impacts the performance of ML models, our survey focuses specifically on summarizing VIS4ML works from the data perspective. First, we categorize the common data handled by ML models into five types, explain the unique features of each type, and highlight the corresponding ML models that are good at learning from them. Second, from the large number of VIS4ML works, we tease out six tasks that operate on these types of data (i.e., data-centric tasks) at different stages of the ML pipeline to understand, diagnose, and refine ML models. Lastly, by studying the distribution of 143 surveyed papers across the five data types, six data-centric tasks, and their intersections, we analyze the prospective research directions and envision future research trends.