Knowledge-based Residual Learning

Knowledge-based Residual Learning

Guanjie Zheng, Chang Liu, Hua Wei, Porter Jenkins, Chacha Chen, Tao Wen, Zhenhui Li

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
Main Track. Pages 1653-1659. https://doi.org/10.24963/ijcai.2021/228

Small data has been a barrier for many machine learning tasks, especially when applied in scientific domains. Fortunately, we can utilize domain knowledge to make up the lack of data. Hence, in this paper, we propose a hybrid model KRL that treats domain knowledge model as a weak learner and uses another neural net model to boost it. We prove that KRL is guaranteed to improve over pure domain knowledge model and pure neural net model under certain loss functions. Extensive experiments have shown the superior performance of KRL over baselines. In addition, several case studies have explained how the domain knowledge can assist the prediction.
Keywords:
Data Mining: Classification
Data Mining: Mining Spatial, Temporal Data
Data Mining: Theoretical Foundation of Data Mining