GANViz: A Visual Analytics Approach to Understand the Adversarial Game

• Published in: IEEE transactions on visualization and computer graphics Vol. 24; no. 6; pp. 1905 - 1917
• Main Authors: Wang, Junpeng, Gou, Liang, Yang, Hao, Shen, Han-Wei
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.06.2018; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Analytical models; Analytics; Computer Science; deep learning; Feature extraction; Gallium nitride; Generative adversarial nets; Machine learning; model interpretation; Neural networks; Neurons; Subject specialists; Training; Visual analytics
• ISSN: 1077-2626; 1941-0506; 1941-0506
• DOI: 10.1109/TVCG.2018.2816223

Generative models bear promising implications to learn data representations in an unsupervised fashion with deep learning. Generative Adversarial Nets (GAN) is one of the most popular frameworks in this arena. Despite the promising results from different types of GANs, in-depth understanding on the adversarial training process of the models remains a challenge to domain experts. The complexity and the potential long-time training process of the models make it hard to evaluate, interpret, and optimize them. In this work, guided by practical needs from domain experts, we design and develop a visual analytics system, GANViz, aiming to help experts understand the adversarial process of GANs in-depth. Specifically, GANViz evaluates the model performance of two subnetworks of GANs, provides evidence and interpretations of the models' performance, and empowers comparative analysis with the evidence. Through our case studies with two real-world datasets, we demonstrate that GANViz can provide useful insight into helping domain experts understand, interpret, evaluate, and potentially improve GAN models.