Neural-based classification rule learning for sequential data
This work addresses the need for interpretable classification in fields like genomics and fraud detection, though it appears incremental as it builds on existing neural and rule-based approaches.
The authors tackled the problem of discovering interpretable patterns for binary classification of sequential data, proposing a differentiable method that learns expressive patterns alongside rules, and demonstrated its validity on synthetic and peptides datasets.
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.