The Bid Picture: Auction-Inspired Multi-player Generative Adversarial Networks Training
This addresses mode collapse in generative models for AI researchers, but appears incremental as it builds on existing GAN frameworks.
The paper tackles the mode collapse problem in GANs by proposing an auction-inspired multi-player training approach, which extends the two-player game to multiple players and uses bids to determine model values, though no concrete performance numbers are provided.
This article proposes auction-inspired multi-player generative adversarial networks training, which mitigates the mode collapse problem of GANs. Mode collapse occurs when an over-fitted generator generates a limited range of samples, often concentrating on a small subset of the data distribution. Despite the restricted diversity of generated samples, the discriminator can still be deceived into distinguishing these samples as real samples from the actual distribution. In the absence of external standards, a model cannot recognize its failure during the training phase. We extend the two-player game of generative adversarial networks to the multi-player game. During the training, the values of each model are determined by the bids submitted by other players in an auction-like process.