论文标题
欢呼：丰富的模型通过知识输液来帮助糟糕的模型
CHEER: Rich Model Helps Poor Model via Knowledge Infusion
论文作者
论文摘要
在富数据环境中具有多个功能渠道的数据驱动的驱动（例如重症监护单元），对将深度学习（DL）应用于医疗保健越来越兴趣。但是，在许多其他实际情况下，我们只能在贫困数据环境（例如在家中）访问具有更少特征渠道的数据，这通常会导致性能差的预测模型。我们如何通过利用从相关环境中使用丰富数据训练的现有模型中提取的知识来提高从如此贫穷的环境中学到的模型的性能？为了解决这个问题，我们开发了一个名为Cheer的知识输液框架，可以将这种丰富的模型简要汇总到可转移的表示形式中，可以将其纳入较差的模型中以提高其性能。理论上对注入的模型进行了分析，并在几个数据集上进行了经验评估。我们的经验结果表明，就多个生理数据集的宏F1分数而言，Cheer的表现优于5.60％至46.80％。
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.
