# Influence Estimation for Generative Adversarial Networks

arXiv: https://arxiv.org/abs/2101.08367 · HTML: https://mlsanity.com/paper/2101.08367/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 29 references that are in the map.
- First posted on arXiv 20 Jan 2021.

## Builds on (most cited first, 18 of 18)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling](https://mlsanity.com/paper/1610.07584/) (2016)
- [Data Augmentation Generative Adversarial Networks](https://mlsanity.com/paper/1711.04340/) (2017)
- [Pros and Cons of GAN Evaluation Measures](https://mlsanity.com/paper/1802.03446/) (2018)
- [A Variational Inequality Perspective on Generative Adversarial Networks](https://mlsanity.com/paper/1802.10551/) (2018)
- [Data Cleansing for Models Trained with SGD](https://mlsanity.com/paper/1906.08473/) (2019)
- [Interpreting Black Box Predictions using Fisher Kernels](https://mlsanity.com/paper/1810.10118/) (2018)
- [AdaGAN: Boosting Generative Models](https://mlsanity.com/paper/1701.02386/) (2017)
- [An Improved Evaluation Framework for Generative Adversarial Networks](https://mlsanity.com/paper/1803.07474/) (2018)
- [Noise Robust Generative Adversarial Networks](https://mlsanity.com/paper/1911.11776/) (2019)

## Built on by (most cited first, 11 of 11)

- [Training Data Influence Analysis and Estimation: A Survey](https://mlsanity.com/paper/2212.04612/) (2022)
- [On Memorization in Probabilistic Deep Generative Models](https://mlsanity.com/paper/2106.03216/) (2021)
- [Intriguing Properties of Data Attribution on Diffusion Models](https://mlsanity.com/paper/2311.00500/) (2023)
- [Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Models](https://mlsanity.com/paper/2410.18639/) (2024)
- [Understanding Instance-based Interpretability of Variational Auto-Encoders](https://mlsanity.com/paper/2105.14203/) (2021)
- [Adapting and Evaluating Influence-Estimation Methods for Gradient-Boosted Decision Trees](https://mlsanity.com/paper/2205.00359/) (2022)
- [Data Attribution for Diffusion Models: Timestep-induced Bias in Influence Estimation](https://mlsanity.com/paper/2401.09031/) (2024)
- [GMValuator: Similarity-based Data Valuation for Generative Models](https://mlsanity.com/paper/2304.10701/) (2023)
- [Thresholding Data Shapley for Data Cleansing Using Multi-Armed Bandits](https://mlsanity.com/paper/2402.08209/) (2024)
- [Data Cleansing for GANs](https://mlsanity.com/paper/2504.00603/) (2025)
- [Distilling Diffusion Score Discrepancy for Efficient Training Data Attribution](https://mlsanity.com/paper/2609.38776/) (2026)

## Abstract (arXiv)

Identifying harmful instances, whose absence in a training dataset improves model performance, is important for building better machine learning models. Although previous studies have succeeded in estimating harmful instances under supervised settings, they cannot be trivially extended to generative adversarial networks (GANs). This is because previous approaches require that (1) the absence of a training instance directly affects the loss value and that (2) the change in the loss directly measures the harmfulness of the instance for the performance of a model. In GAN training, however, neither of the requirements is satisfied. This is because, (1) the generator's loss is not directly affected by the training instances as they are not part of the generator's training steps, and (2) the values of GAN's losses normally do not capture the generative performance of a model. To this end, (1) we propose an influence estimation method that uses the Jacobian of the gradient of the generator's loss with respect to the discriminator's parameters (and vice versa) to trace how the absence of an instance in the discriminator's training affects the generator's parameters, and (2) we propose a novel evaluation scheme, in which we assess harmfulness of each training instance on the basis of how GAN evaluation metric (e.g., inception score) is expect to change due to the removal of the instance. We experimentally verified that our influence estimation method correctly inferred the changes in GAN evaluation metrics. Further, we demonstrated that the removal of the identified harmful instances effectively improved the model's generative performance with respect to various GAN evaluation metrics.