Editable Neural Networks

Anton Sinitsin, Vsevolod Plokhotnyuk, Dmitry Pyrkin, Sergei Popov, Artem Babenko

Keywords: editing, editable, meta-learning, maml

TL;DR: Training neural networks so you can efficiently patch them later.

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.

Code: https://github.com/editable-ICLR2020/editable

Community Implementations: [ 3 code implementations](https://www.catalyzex.com/paper/arxiv:2004.00345/code)