Second-Order Group Influence Functions for Black-Box Predictions

11/01/2019
by   Samyadeep Basu, et al.
22

With the rapid adoption of machine learning systems in sensitive applications, there is an increasing need to make black-box models explainable. Often we want to identify an influential group of training samples in a particular test prediction. Existing influence functions tackle this problem by using first-order approximations of the effect of removing a sample from the training set on model parameters. To compute the influence of a group of training samples (rather than an individual point) in model predictions, the change in optimal model parameters after removing that group from the training set can be large. Thus, in such cases, the first-order approximation can be loose. In this paper, we address this issue and propose second-order influence functions for identifying influential groups in test-time predictions. For linear models and across different sizes of groups, we show that using the proposed second-order influence function improves the correlation between the computed influence values and the ground truth ones. For nonlinear models based on neural networks, we empirically show that none of the existing first-order and the proposed second-order influence functions provide proper estimates of the ground-truth influences over all training samples. We empirically study this phenomenon by decomposing the influence values over contributions from different eigenvectors of the Hessian of the trained model.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/14/2017

Understanding Black-box Predictions via Influence Functions

How can we explain the predictions of a black-box model? In this paper, ...
research
05/30/2019

On the Accuracy of Influence Functions for Measuring Group Effects

Influence functions estimate the effect of removing particular training ...
research
06/20/2023

A Model-free Closeness-of-influence Test for Features in Supervised Learning

Understanding the effect of a feature vector x ∈ℝ^d on the response valu...
research
11/01/2020

Transparent Interpretation with Knockouts

How can we find a subset of training samples that are most responsible f...
research
07/08/2021

SSSE: Efficiently Erasing Samples from Trained Machine Learning Models

The availability of large amounts of user-provided data has been key to ...
research
09/12/2022

If Influence Functions are the Answer, Then What is the Question?

Influence functions efficiently estimate the effect of removing a single...
research
10/14/2022

Characterizing the Influence of Graph Elements

Influence function, a method from robust statistics, measures the change...

Please sign up or login with your details

Forgot password? Click here to reset