Efficient Estimation of Influence of a Training Instance

Abstract

Understanding the influence of a training instance on a neural network model leads to improving interpretability. However, it is difficult and inefficient to evaluate the influence, which shows how a model's prediction would be changed if a training instance were not used. In this paper, we propose an efficient method for estimating the influence. Our method is inspired by dropout, which zero-masks a sub-network and prevents the sub-network from learning each training instance. By switching between dropout masks, we can use sub-networks that learned or did not learn each training instance and estimate its influence. Through experiments with BERT and VGGNet on classification datasets, we demonstrate that the proposed method can capture training influences, enhance the interpretability of error predictions, and cleanse the training dataset for improving generalization.

arXiv commentThis is an extended version of the paper presented at SustaiNLP 2020

References in corpus (7)

• Improving neural networks by preventing co-adaptation of feature detectors
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Understanding Black-box Predictions via Influence Functions
• Pointer Sentinel Mixture Models
• Learning with Pseudo-Ensembles
• A critical analysis of self-supervision, or what we can learn from a single image
• Training Set Debugging Using Trusted Items