RDPD: Rich Data Helps Poor Data via Imitation
share
In many situations, we have both rich- and poor- data environments: in a rich-data environment (e.g., intensive care units), we have high-quality multi-modality data. On the other hand, in a poor-data environment (e.g., at home), we often only have access to a single data modality with low quality. How can we learn an accurate and efficient model for the poor-data environment by leveraging multi-modality data from the rich-data environment? In this work, we propose a knowledge distillation model RDPD to enhance a small model trained on poor data with a complex model trained on rich data. In an end-to-end fashion, RDPD trains a student model built on a single modality data (poor data) to imitate the behavior and performance of a teacher model from multimodal data (rich data) via jointly optimizing the combined loss of attention imitation and target imitation. We evaluated RDPD on three real-world datasets. RDPD consistently outperformed all baselines across all three datasets, especially achieving the greatest performance improvement over a standard neural network model trained on the common features (Direct model) by 24.56 distillation model by 5.91
READ FULL TEXT