Improved Training of Spectral Normalization Generative Adversarial Networks

Chao, Xiaopeng; Cao, Jiangzhong; Lu, Yuqin; Dai, Qingyun

doi:10.1109/wsai49636.2020.9143310

Cited by 11 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given the instability of GAN training, evaluation of metrics throughout the training process is important. Further studies could include the use of spectral normalization of the discriminator and L2 norm regularization in the generator to aid in convergence and stability earlier on in the training process [19,20].…”

Section: Training the Gansmentioning

confidence: 99%

Evaluation of synthetic Raman spectra for use in virus detection

Ricker,

Perea,

Ghedin

et al. 2024

Synthetic Data for Artificial Intelligence and Machine Learning: Tools, Techniques, and Applications II

View full text Add to dashboard Cite

A Generative Adversarial Network was used to produce Raman spectra of Influenza A virus in culture and then used to train a virus detection classification model. Dimensionality reduction plotting using t-Distributed Stochastic Neighbor Embedding (t-SNE) demonstrated overlap between the real and synthetic spectra but not complete blending, which can be attributed to the subtle differences between the real and synthetic data. Nevertheless, the real and synthetic spectra also exhibited similar Raman peak patterns. Moreover, the inclusion of synthetic spectra into the training set was able to increase the virus classification accuracy from 83.5% to 91.5%. This indicates that the GANs were able to synthesize spectra closely related to virus-positive spectra yet distinctly different from virus-negative spectra, which appear visually similar. We conclude that the synthetic spectra produced by the GANs were similar to the real data but not an exact replacement.

show abstract

Section: Training the Gansmentioning

confidence: 99%

Evaluation of synthetic Raman spectra for use in virus detection

Ricker,

Perea,

Ghedin

et al. 2024

Synthetic Data for Artificial Intelligence and Machine Learning: Tools, Techniques, and Applications II

View full text Add to dashboard Cite

show abstract

“…Much recent work has been dedicated to better understanding two-player GANs optimization dynamics [Heusel et al, 2017, Li et al, 2018, Mescheder et al, 2017, Miyato et al, 2018, Nie and Patel, 2020, Xiaopeng et al, 2020. This is unsurprising, as many famous GAN use cases rely on a two-player architecture-usually a Generator and a Discriminator.…”

Section: Introductionmentioning

confidence: 99%

Three-Player Game Training Dynamics

Christofferson¹,

Yanez²

2022

Preprint

View full text Add to dashboard Cite

This work explores three-player game training dynamics, under what conditions three-player games converge and the equilibria the converge on. In contrast to prior work, we examine a three-player game architecture in which all players explicitly interact with each other. Prior work analyzes games in which two of three agents interact with only one other player, constituting dual two-player games. We explore three-player game training dynamics using an extended version of a simplified bilinear smooth game, called a simplified trilinear smooth game. We find that trilinear games do not converge on the Nash equilibrium in most cases, rather converging on a fixed point which is optimal for two players, but not for the third. Further, we explore how the order of the updates influences convergence. In addition to alternating and simultaneous updates, we explore a new update order-maximizer-first-which is only possible in a three-player game. We find that three-player games can converge on a Nash equilibrium using maximizer-first updates. Finally, we experiment with differing momentum values for each player in a trilinear smooth game under all three update orders and show that maximizer-first updates achieve more optimal results in a larger set of player-specific momentum value triads than other update orders.* Equal contribution. Listed alphabetically.

show abstract