Influence Approximation

2 papers with code • 0 benchmarks • 0 datasets

Estimating the influence of training triples on the behavior of a machine learning model.

Datasets


Greatest papers with code

On the Accuracy of Influence Functions for Measuring Group Effects

kohpangwei/group-influence-release NeurIPS 2019

Influence functions estimate the effect of removing a training point on a model without the need to retrain.

Influence Approximation

Explaining Neural Matrix Factorization with Gradient Rollback

carolinlawrence/gradient-rollback 12 Oct 2020

Moreover, we show theoretically that the difference between gradient rollback's influence approximation and the true influence on a model's behavior is smaller than known bounds on the stability of stochastic gradient descent.

Influence Approximation Knowledge Base Completion +1