PyHard: a novel tool for generating hardness embeddings to support data-centric analysis

TL;DR

PyHard is a new tool that uses Instance Space Analysis to create a visual, interpretable embedding of dataset hardness, helping to evaluate data quality and model performance in machine learning.

Contribution

It introduces a novel hardness embedding technique that visually reveals data and model strengths and weaknesses, aiding data-centric ML analysis.

Findings

Identified hard observation pockets in COVID prognosis data.

Visualized model strengths and weaknesses across dataset regions.

Supported targeted data inspection and model improvement.

Abstract

For building successful Machine Learning (ML) systems, it is imperative to have high quality data and well tuned learning models. But how can one assess the quality of a given dataset? And how can the strengths and weaknesses of a model on a dataset be revealed? Our new tool PyHard employs a methodology known as Instance Space Analysis (ISA) to produce a hardness embedding of a dataset relating the predictive performance of multiple ML models to estimated instance hardness meta-features. This space is built so that observations are distributed linearly regarding how hard they are to classify. The user can visually interact with this embedding in multiple ways and obtain useful insights about data and algorithmic performance along the individual observations of the dataset. We show in a COVID prognosis dataset how this analysis supported the identification of pockets of hard observations that challenge ML models and are therefore worth closer inspection, and the delineation of regions of strengths and weaknesses of ML models.