Editable Neural Networks

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 consequ...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-07
Main Authors: Sinitsin, Anton, Plokhotnyuk, Vsevolod, Pyrkin, Dmitriy, Popov, Sergei, Babenko, Artem
Format: Article
Language:English
Subjects:
Artificial neural networks
Autonomous cars
Editing
Image classification
Machine translation
Neural networks
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422