Multi-population GAN Training: Analyzing Co-Evolutionary Algorithms

• URL: http://arxiv.org/abs/2507.13157v1
• Date: Thu, 17 Jul 2025 14:19:17 GMT
• Title: Multi-population GAN Training: Analyzing Co-Evolutionary Algorithms
• Authors: Walter P. Casas, Jamal Toutouh,
• Abstract summary: Generative adversarial networks (GANs) are powerful generative models but remain challenging to train due to pathologies such as mode collapse and instability.<n>Recent research has explored co-evolutionary approaches, in which populations of generators and discriminators are evolved.<n>This paper presents an empirical analysis of different coevolutionary GAN training strategies, focusing on the impact of selection and replacement mechanisms.
• Score: 0.3683202928838613
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative adversarial networks (GANs) are powerful generative models but remain challenging to train due to pathologies suchas mode collapse and instability. Recent research has explored co-evolutionary approaches, in which populations of generators and discriminators are evolved, as a promising solution. This paper presents an empirical analysis of different coevolutionary GAN training strategies, focusing on the impact of selection and replacement mechanisms. We compare (mu,lambda), (mu+lambda) with elitism, and (mu+lambda) with tournament selection coevolutionary schemes, along with a non-evolutionary population based multi-generator multi-discriminator GAN baseline, across both synthetic low-dimensional datasets (blob and gaussian mixtures) and an image-based benchmark (MNIST). Results show that full generational replacement, i.e., (mu,lambda), consistently outperforms in terms of both sample quality and diversity, particularly when combined with larger offspring sizes. In contrast, elitist approaches tend to converge prematurely and suffer from reduced diversity. These findings highlight the importance of balancing exploration and exploitation dynamics in coevolutionary GAN training and provide guidance for designing more effective population-based generative models.

Related papers

• Generate more than one child in your co-evolutionary semi-supervised learning GAN [1.3927943269211591]
  SSL-GAN has attracted many researchers in the last decade.<n>Co-evolutionary approaches have been applied where the two networks of a GAN are evolved in separate populations.<n>We propose a new co-evolutionary approach, called Co-evolutionary Elitist SSL-GAN (CE-SSLGAN), with panmictic population, elitist replacement, and more than one individual in the offspring.
  arXiv  Detail & Related papers  (2025-04-29T09:04:22Z)
• Heuristically Adaptive Diffusion-Model Evolutionary Strategy [1.8299322342860518]
  Diffusion Models represent a significant advancement in generative modeling. Our research reveals a fundamental connection between diffusion models and evolutionary algorithms. Our framework marks a major algorithmic transition, offering increased flexibility, precision, and control in evolutionary optimization processes.
  arXiv  Detail & Related papers  (2024-11-20T16:06:28Z)
• When Large Language Models Meet Evolutionary Algorithms: Potential Enhancements and Challenges [50.280704114978384]
  Pre-trained large language models (LLMs) exhibit powerful capabilities for generating natural text.<n> Evolutionary algorithms (EAs) can discover diverse solutions to complex real-world problems.
  arXiv  Detail & Related papers  (2024-01-19T05:58:30Z)
• DARLEI: Deep Accelerated Reinforcement Learning with Evolutionary Intelligence [77.78795329701367]
  We present DARLEI, a framework that combines evolutionary algorithms with parallelized reinforcement learning. We characterize DARLEI's performance under various conditions, revealing factors impacting diversity of evolved morphologies. We hope to extend DARLEI in future work to include interactions between diverse morphologies in richer environments.
  arXiv  Detail & Related papers  (2023-12-08T16:51:10Z)
• EGANS: Evolutionary Generative Adversarial Network Search for Zero-Shot Learning [13.275693216436494]
  We propose evolutionary generative adversarial network search (EGANS) to automatically design the generative network with good adaptation and stability. EGANS is learned by two stages: evolution generator architecture search and evolution discriminator architecture search. Experiments show that EGANS consistently improve existing generative ZSL methods on the standard CUB, SUN, AWA2 and FLO datasets.
  arXiv  Detail & Related papers  (2023-08-19T05:47:03Z)
• Improving Out-of-Distribution Robustness of Classifiers via Generative Interpolation [56.620403243640396]
  Deep neural networks achieve superior performance for learning from independent and identically distributed (i.i.d.) data. However, their performance deteriorates significantly when handling out-of-distribution (OoD) data. We develop a simple yet effective method called Generative Interpolation to fuse generative models trained from multiple domains for synthesizing diverse OoD samples.
  arXiv  Detail & Related papers  (2023-07-23T03:53:53Z)
• Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data [125.7135706352493]
  Generative adversarial networks (GANs) typically require ample data for training in order to synthesize high-fidelity images. Recent studies have shown that training GANs with limited data remains formidable due to discriminator overfitting. This paper introduces a novel strategy called Adaptive Pseudo Augmentation (APA) to encourage healthy competition between the generator and the discriminator.
  arXiv  Detail & Related papers  (2021-11-12T18:13:45Z)
• cMLSGA: A Co-Evolutionary Multi-Level Selection Genetic Algorithm for Multi-Objective Optimization [0.0]
  Multi-Level Selection Genetic Algorithm (MLSGA) already shows good performance on range of problems. This paper proposes a distinct set of co-evolutionary mechanisms, which defines co-evolution as competition between collectives rather than individuals.
  arXiv  Detail & Related papers  (2021-04-22T13:52:21Z)
• Epigenetic evolution of deep convolutional models [81.21462458089142]
  We build upon a previously proposed neuroevolution framework to evolve deep convolutional models. We propose a convolutional layer layout which allows kernels of different shapes and sizes to coexist within the same layer. The proposed layout enables the size and shape of individual kernels within a convolutional layer to be evolved with a corresponding new mutation operator.
  arXiv  Detail & Related papers  (2021-04-12T12:45:16Z)
• GANs with Variational Entropy Regularizers: Applications in Mitigating the Mode-Collapse Issue [95.23775347605923]
  Building on the success of deep learning, Generative Adversarial Networks (GANs) provide a modern approach to learn a probability distribution from observed samples. GANs often suffer from the mode collapse issue where the generator fails to capture all existing modes of the input distribution. We take an information-theoretic approach and maximize a variational lower bound on the entropy of the generated samples to increase their diversity.
  arXiv  Detail & Related papers  (2020-09-24T19:34:37Z)
• Analyzing the Components of Distributed Coevolutionary GAN Training [8.198369743955528]
  We investigate the impact on the performance of two algorithm components that influence the diversity during coevolution. In experiments on MNIST dataset, we find that the combination of these two components provides the best generative models.
  arXiv  Detail & Related papers  (2020-08-03T18:35:06Z)
• Towards Multimodal Response Generation with Exemplar Augmentation and Curriculum Optimization [73.45742420178196]
  We propose a novel multimodal response generation framework with exemplar augmentation and curriculum optimization. Our model achieves significant improvements compared to strong baselines in terms of diversity and relevance.
  arXiv  Detail & Related papers  (2020-04-26T16:29:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.