Knowledge-based Residual Learning

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

IJCAI 2021poster6 citations

Knowledge-based Residual Learning

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

Abstract

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.

Data Mining: ClassificationData Mining: Mining Spatial, Temporal DataData Mining: Theoretical Foundation of Data Mining

BibTeX

@inproceedings{ijcai2021p228,
  title     = {Knowledge-based Residual Learning},
  author    = {Zheng, Guanjie and Liu, Chang and Wei, Hua and Jenkins, Porter and Chen, Chacha and Wen, Tao and Li, Zhenhui},
  booktitle = {Proceedings of the Thirtieth International Joint Conference on
               Artificial Intelligence, {IJCAI-21}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Zhi-Hua Zhou},
  pages     = {1653--1659},
  year      = {2021},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2021/228},
  url       = {https://doi.org/10.24963/ijcai.2021/228},
}