CHEER: Rich Model Helps Poor Model via Knowledge Infusion

TL;DR

CHEER is a framework that enhances poor-data models by infusing knowledge from rich-data models, significantly improving performance in healthcare prediction tasks.

Contribution

We introduce CHEER, a novel knowledge infusion method that transfers insights from rich-data models to poor-data models, boosting their accuracy.

Findings

CHEER outperformed baselines by up to 46.80% in macro-F1 score.

Theoretical analysis supports the effectiveness of knowledge infusion.

Empirical evaluation on multiple datasets confirms performance improvements.

Abstract

There is a growing interest in applying deep learning (DL) to healthcare, driven by the availability of data with multiple feature channels in rich-data environments (e.g., intensive care units). However, in many other practical situations, we can only access data with much fewer feature channels in a poor-data environments (e.g., at home), which often results in predictive models with poor performance. How can we boost the performance of models learned from such poor-data environment by leveraging knowledge extracted from existing models trained using rich data in a related environment? To address this question, we develop a knowledge infusion framework named CHEER that can succinctly summarize such rich model into transferable representations, which can be incorporated into the poor model to improve its performance. The infused model is analyzed theoretically and evaluated empirically on several datasets. Our empirical results showed that CHEER outperformed baselines by 5.60% to 46.80% in terms of the macro-F1 score on multiple physiological datasets.