Population-Based Multi-Objective Training of Discriminators for Semi-Supervised GANs

2026-07-02

AI Summary

This work addresses the instability in semi-supervised GAN training caused by the inherent conflict between maximizing classification accuracy and enhancing the discriminator’s ability to distinguish real from fake samples. To resolve this, the study introduces a multi-objective evolutionary algorithm into the training framework for the first time, formulating discriminator optimization as a multi-objective problem. By leveraging population-based evolutionary strategies and Pareto dominance, the method preserves a diverse set of non-dominated solutions without resorting to scalar loss aggregation. Evaluated on label-limited MNIST, the approach significantly improves training stability, and its elite variant achieves state-of-the-art classification accuracy, outperforming baseline models such as SSL-GAN and CE-SSL-GAN.

Abstract

Semi-supervised generative adversarial networks (SSL-GANs) can exploit large unlabeled datasets while retaining a classifier in the discriminator, but their training is often unstable. This paper proposes a population-based evolutionary training strategy in which discriminator learning is formulated as a multi-objective optimization problem. Instead of aggregating the supervised and unsupervised components of the SSL objective into a single scalar loss, the method maintains a population of discriminators ranked by Pareto dominance, enabling the exploration of different trade-offs between classification accuracy and real/fake discrimination. This formulation aims to improve both roles of SSL-GANs: learning accurate classifiers and training generators capable of producing realistic samples. We analyze several variants, including an elitist strategy and a mono-objective ablation, to assess the role of multi-objective selection. Experiments on MNIST with limited labels show improved training robustness compared to SSL-GAN and CE-SSL-GAN state-of-the-art baselines, while the elitist variant consistently achieves the highest classification accuracy.

Problem

• Semi-supervised GANs
• Training instability
• Multi-objective optimization
• Discriminator training
• Classification accuracy

Innovation

• population-based training
• multi-objective optimization
• semi-supervised GANs
• Pareto dominance
• evolutionary strategy