Neural-based classification rule learning for sequential data
Marine Collery, Philippe Bonnard, François Fages, Remy Kusters
Abstract
Discovering interpretable patterns for classification of sequential data is of key importance for a variety of fields, ranging from genomics to fraud detection or more generally interpretable decision-making. In this paper, we propose a novel differentiable fully interpretable method to discover both local and global patterns (i.e. catching a relative or absolute temporal dependency) for rule-based binary classification. It consists of a convolutional binary neural network with an interpretable neural filter and a training strategy based on dynamically-enforced sparsity. We demonstrate the validity and usefulness of the approach on synthetic datasets and on an open-source peptides dataset. Key to this end-to-end differentiable method is that the expressive patterns used in the rules are learned alongside the rules themselves.
BibTeX
@inproceedings{
collery2023neuralbased,
title={Neural-based classification rule learning for sequential data},
author={Marine Collery and Philippe Bonnard and Fran{\c{c}}ois Fages and Remy Kusters},
booktitle={The Eleventh International Conference on Learning Representations },
year={2023},
url={https://openreview.net/forum?id=7tJyBmu9iCj}
}