Editable Neural Networks

Code

• github.com/xtinkt/editable
  OfficialIn paperpytorch★ 46
• github.com/editable-ICLR2020/editable
  OfficialIn paperpytorch★ 32
• github.com/eric-mitchell/mend
  pytorch★ 257
• github.com/Recognito-Vision/Android-FaceRecognition-FaceLivenessDetection
  none★ 110
• github.com/eric-mitchell/serac
  pytorch★ 72

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.

Tasks

Reproductions