Knowledge-based Residual Learning

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

doi:10.24963/ijcai.2021/228

Knowledge-based Residual Learning

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

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 1653-1659.

https://doi.org/10.24963/ijcai.2021/228

Keywords

Data Mining: Mining Spatial, Temporal Data
Data Mining: Classification
Data Mining: Theoretical Foundation of Data Mining

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.

Guanjie Zheng, Chang Liu, Hua Wei, Porter Jenkins, Chacha Chen, Tao Wen, and Zhenhui Li. 2021. Knowledge-based Residual Learning. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 1653–1659. https://doi.org/10.24963/ijcai.2021/228

@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    = {Prof. 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},
}

TY  - CPAPER
TI  - Knowledge-based Residual Learning
AU  - Zheng, Guanjie
AU  - Liu, Chang
AU  - Wei, Hua
AU  - Jenkins, Porter
AU  - Chen, Chacha
AU  - Wen, Tao
AU  - Li, Zhenhui
T2  - Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2021
SP  - 1653
EP  - 1659
DO  - 10.24963/ijcai.2021/228
UR  - https://doi.org/10.24963/ijcai.2021/228
ER  -