Title: Scaling Up Influence Functions
Authors: Andrea Schioppa, Polina Zablotskaia, David Vilar, Artem Sokolov
Published: 6th December 2021 (Monday) @ 13:54:08
Link: http://arxiv.org/abs/2112.03052v1
Abstract
We address efficient calculation of influence functions for tracking predictions back to the training data. We propose and analyze a new approach to speeding up the inverse Hessian calculation based on Arnoldi iteration. With this improvement, we achieve, to the best of our knowledge, the first successful implementation of influence functions that scales to full-size (language and vision) Transformer models with several hundreds of millions of parameters. We evaluate our approach on image classification and sequence-to-sequence tasks with tens to a hundred of millions of training examples. Our code will be available at https://github.com/google-research/jax-influence.