CHEER: Rich Model Helps Poor Model via Knowledge Infusion.

There is a growing interest in applying deep learning (DL) to healthcare, driven by the availability of data with multiple feature channels in environments (e.g., intensive care units). However, in many other practical situations, we can only access data with much fewer feature channels in a 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 environment by leveraging knowledge extracted from existing models trained using in a related environment? To address this question, we develop a knowledge infusion framework named CHEER that can succinctly summarize such into transferable representations, which can be incorporated into the 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.