Distributional Adversarial Networks

2017/06/29 by Chengtao Li, David Alvarez-Melis, Li, Chengtao +7 · 1 citation
Computer Science · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.1706.09549

openalex publication_date 2017/06/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We propose a framework for adversarial training that relies on a sample rather than a single sample point as the fundamental unit of discrimination. Inspired by discrepancy measures and two-sample tests between probability distributions, we propose two such distributional adversaries that operate and predict on samples, and show how they can be easily implemented on top of existing models. Various experimental results show that generators trained with our distributional adversaries are much more stable and are remarkably less prone to mode collapse than traditional models trained with pointwise prediction discriminators. The application of our framework to domain adaptation also results in considerable improvement over recent state-of-the-art.

Citations

• Adam: A Method for Stochastic Optimization
• Energy-based Generative Adversarial Network
• Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
• Unrolled Generative Adversarial Networks
• Mode Regularized Generative Adversarial Networks
• Quality Aware Network for Set to Set Recognition
• Generating Videos with Scene Dynamics
• Adversarial Discriminative Domain Adaptation
• Training generative neural networks via Maximum Mean Discrepancy optimization

Cited by

• Dist-GAN: An Improved GAN using Distance Constraints

Related

• Adversarial Distributional Training for Robust Deep Learning
• Out-distribution training confers robustness to deep neural networks
• Enhancing Adversarial Robustness via Uncertainty-Aware Distributional Adversarial Training
• Generative Adversarial Networks
• Fundamental Tradeoffs in Distributionally Adversarial Training