# Importance Weighted Generative Networks

arXiv: https://arxiv.org/abs/1806.02512 · HTML: https://mlsanity.com/paper/1806.02512/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jun 2018.

## Built on by (most cited first, 7 of 7)

- [Unaligned Image-to-Image Translation by Learning to Reweight](https://mlsanity.com/paper/2109.11736/) (2021)
- [Fairness Without Harm: An Influence-Guided Active Sampling Approach](https://mlsanity.com/paper/2402.12789/) (2024)
- [Fast and Accurate Importance Weighting for Correcting Sample Bias](https://mlsanity.com/paper/2209.04215/) (2022)
- [Leverage Score Sampling for Complete Mode Coverage in Generative Adversarial Networks](https://mlsanity.com/paper/2104.02373/) (2021)
- [DCAST: Diverse Class-Aware Self-Training Mitigates Selection Bias for Fairer Learning](https://mlsanity.com/paper/2409.20126/) (2024)
- [Regularized Generative Adversarial Network](https://mlsanity.com/paper/2102.04593/) (2021)
- [Dynamics of Fourier Modes in Torus Generative Adversarial Networks](https://mlsanity.com/paper/2209.01842/) (2022)

## Abstract (arXiv)

Deep generative networks can simulate from a complex target distribution, by minimizing a loss with respect to samples from that distribution. However, often we do not have direct access to our target distribution - our data may be subject to sample selection bias, or may be from a different but related distribution. We present methods based on importance weighting that can estimate the loss with respect to a target distribution, even if we cannot access that distribution directly, in a variety of settings. These estimators, which differentially weight the contribution of data to the loss function, offer both theoretical guarantees and impressive empirical performance.