ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2206.10013
21
52

Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments

20 June 2022
Jinkun Lin
Anqi Zhang
Mathias Lécuyer
Jinyang Li
Aurojit Panda
S. Sen
    TDI
    FedML
ArXivPDFHTML
Abstract

We develop a new, principled algorithm for estimating the contribution of training data points to the behavior of a deep learning model, such as a specific prediction it makes. Our algorithm estimates the AME, a quantity that measures the expected (average) marginal effect of adding a data point to a subset of the training data, sampled from a given distribution. When subsets are sampled from the uniform distribution, the AME reduces to the well-known Shapley value. Our approach is inspired by causal inference and randomized experiments: we sample different subsets of the training data to train multiple submodels, and evaluate each submodel's behavior. We then use a LASSO regression to jointly estimate the AME of each data point, based on the subset compositions. Under sparsity assumptions (k≪Nk \ll Nk≪N datapoints have large AME), our estimator requires only O(klog⁡N)O(k\log N)O(klogN) randomized submodel trainings, improving upon the best prior Shapley value estimators.

View on arXiv
Comments on this paper