paper-with-me

Papers

DSF-GAN: DownStream Feedback Generative Adversarial Network

2024-03-27 · Oriel Perets, Nadav Rappoport

Utility and privacy are two crucial measurements of the quality of synthetic tabular data. While significant advancements have been made in privacy measures, generating synthetic samples with high utility remains challenging. To enhance the utility of synthetic samples, we propose a novel architecture called the DownStream Feedback Generative Adversarial Network (DSF-GAN). This approach incorporates feedback from a downstream prediction model during training to augment the generator's loss function with valuable information. Thus, DSF-GAN utilizes a downstream prediction task to enhance the utility of synthetic samples. To evaluate our method, we tested it using two popular datasets. Our experiments demonstrate improved model performance when training on synthetic samples generated by DSF-GAN, compared to those generated by the same GAN architecture without feedback. The evaluation was conducted on the same validation set comprising real samples. All code and datasets used in this research will be made openly available for ease of reproduction.

📄 PDF Abstract BibTeX arXiv:2403.18267

Code (1)

nadavlab/DSF-GAN 공식 구현 pytorch

Tasks

Generative Adversarial Network

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Feedback Adversarial Learning: Spatial Feedback for Improving Generative Adversarial Networks

2019-06-01 · CVPR 2019 6 · Minyoung Huh, Shao-Hua Sun, Ning Zhang

We propose feedback adversarial learning (FAL) framework that can improve existing generative adversarial networks by leveraging spatial feedback from the discriminator. We formulate the generation task as a recurrent fr…

Image GenerationImage-to-Image TranslationTranslation

Neural Networks with Recurrent Generative Feedback

2020-07-17 · NeurIPS 2020 12 · Yujia Huang, James Gornet, Sihui Dai, Zhiding Yu 외

Neural networks are vulnerable to input perturbations such as additive noise and adversarial attacks. In contrast, human perception is much more robust to such perturbations. The Bayesian brain hypothesis states that hum…

Adversarial Robustness

Generative Market Equilibrium Models with Stable Adversarial Learning via Reinforcement

2025-04-05 · Anastasis Kratsios, Xiaofei Shi, Qiang Sun, Zhanhao Zhang

We present a general computational framework for solving continuous-time financial market equilibria under minimal modeling assumptions while incorporating realistic financial frictions, such as trading costs, and suppor…

Deep Reinforcement Learning

Nearly Optimal Algorithms for Contextual Dueling Bandits from Adversarial Feedback

2024-04-16 · Qiwei Di, Jiafan He, Quanquan Gu

Learning from human feedback plays an important role in aligning generative models, such as large language models (LLM). However, the effectiveness of this approach can be influenced by adversaries, who may intentionally…

Ensemble Generative Cleaning with Feedback Loops for Defending Adversarial Attacks

2020-04-23 · CVPR 2020 6 · Jianhe Yuan, Zhihai He

Effective defense of deep neural networks against adversarial attacks remains a challenging problem, especially under powerful white-box attacks. In this paper, we develop a new method called ensemble generative cleaning…