Preventing RNN from Using Sequence Length as a Feature
Machine Learning
2022-12-19 v1
Abstract
Recurrent neural networks are deep learning topologies that can be trained to classify long documents. However, in our recent work, we found a critical problem with these cells: they can use the length differences between texts of different classes as a prominent classification feature. This has the effect of producing models that are brittle and fragile to concept drift, can provide misleading performances and are trivially explainable regardless of text content. This paper illustrates the problem using synthetic and real-world data and provides a simple solution using weight decay regularization.
Cite
@article{arxiv.2212.08276,
title = {Preventing RNN from Using Sequence Length as a Feature},
author = {Jean-Thomas Baillargeon and Hélène Cossette and Luc Lamontagne},
journal= {arXiv preprint arXiv:2212.08276},
year = {2022}
}
Comments
6 pages, but my overleaf generrates 5 pages. I have no error, the font size seems different