A Simple and Efficient Baseline for Data Attribution on Images

November 03, 2023 · Entered Twilight · 🏛 arXiv.org

Repo contents: .gitignore, LICENSE, README.md, constants.py, counterfactual_search.py, environment.yml, features_to_topk_matrix.py, models, self_supervised_models, train_utils.py

Authors Vasu Singla, Pedro Sandoval-Segura, Micah Goldblum, Jonas Geiping, Tom Goldstein arXiv ID 2311.03386 Category cs.CV: Computer Vision Cross-listed cs.LG Citations 6 Venue arXiv.org Repository https://github.com/vasusingla/simple-data-attribution ⭐ 11 Last Checked 3 months ago

Abstract

Data attribution methods play a crucial role in understanding machine learning models, providing insight into which training data points are most responsible for model outputs during deployment. However, current state-of-the-art approaches require a large ensemble of as many as 300,000 models to accurately attribute model predictions. These approaches therefore come at a high computational cost, are memory intensive, and are hard to scale to large models or datasets. In this work, we focus on a minimalist baseline, utilizing the feature space of a backbone pretrained via self-supervised learning to perform data attribution. Our method is model-agnostic and scales easily to large datasets. We show results on CIFAR-10 and ImageNet, achieving strong performance that rivals or outperforms state-of-the-art approaches at a fraction of the compute or memory cost. Contrary to prior work, our results reinforce the intuition that a model's prediction on one image is most impacted by visually similar training samples. Our approach serves as a simple and efficient baseline for data attribution on images.