Training neural networks with classification rules for incorporating domain knowledge

Page view(s)
40
Checked on Feb 12, 2025
Training neural networks with classification rules for incorporating domain knowledge
Title:
Training neural networks with classification rules for incorporating domain knowledge
Journal Title:
Knowledge-Based Systems
Publication Date:
28 March 2024
Citation:
Zhang, W., Liu, F., Nguyen, C. M., Ou Yang, Z. L., Ramasamy, S., & Foo, C.-S. (2024). Training neural networks with classification rules for incorporating domain knowledge. Knowledge-Based Systems, 294, 111716. https://doi.org/10.1016/j.knosys.2024.111716
Abstract:
Neural networks are capable of learning complex concepts and tasks, given abundant training data. In real-world applications where data collection can be difficult, integrating domain knowledge into the model can reduce the burden on data requirements and allow human experts greater control over model decisions. This paper focuses on incorporating conditional statements for tabular data as classification rules, which have a simple structure and are easy to construct. We introduce a general rule loss constraint to guide neural network training in a model agnostic manner, and propose confidence learning to automatically weigh the contribution of multiple candidate rules. Experimental evaluation with three real-world datasets shows that the rule loss can substantially increase model performance, particularly when training data is limited.
License type:
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)
Funding Info:
This research / project is supported by the A*STAR - AME Programmatic Funds
Grant Reference no. : A20H6b0151

This research / project is supported by the A*STAR - IAF-ICP
Grant Reference no. : I2001E0076
Description:
ISSN:
0950-7051
Files uploaded:

File Size Format Action
training-neural-networks-with-classification-rules-for-incorporating-domain-knowledge.pdf 466.14 KB PDF Request a copy