English

Editable Neural Networks

Machine Learning 2020-07-23 v2 Machine Learning

Abstract

These days deep neural networks are ubiquitously used in a wide range of tasks, from image classification and machine translation to face identification and self-driving cars. In many applications, a single model error can lead to devastating financial, reputational and even life-threatening consequences. Therefore, it is crucially important to correct model mistakes quickly as they appear. In this work, we investigate the problem of neural network editing - how one can efficiently patch a mistake of the model on a particular sample, without influencing the model behavior on other samples. Namely, we propose Editable Training, a model-agnostic training technique that encourages fast editing of the trained model. We empirically demonstrate the effectiveness of this method on large-scale image classification and machine translation tasks.

Keywords

Cite

@article{arxiv.2004.00345,
  title  = {Editable Neural Networks},
  author = {Anton Sinitsin and Vsevolod Plokhotnyuk and Dmitriy Pyrkin and Sergei Popov and Artem Babenko},
  journal= {arXiv preprint arXiv:2004.00345},
  year   = {2020}
}
R2 v1 2026-06-23T14:35:06.278Z