Overview and Scope
Generative Machine Learning has become a key field in machine learning and deep learning. In recent years, this field of research has proposed many deep generative models (DGMs) that range from a broad family of methods such as large language models (LLMs), generative adversarial networks (GANs), variational autoencoders (VAEs), Transformers, autoregressive (AR) models and diffusion models (DM). Although these methods have achieved state-of-the-art results in the generation of synthetic data of different types, such as images, speech, text, molecules, video, etc., Deep generative models are still difficult to train, optimize, and fine tune.
There are still open problems, such as the vanishing gradient and mode collapse in DGMs, which limit their performance. Although there are strategies to minimize the effect of those problems, they remain fundamentally unsolved. In recent years, evolutionary computation (EC) and related bio-inspired techniques (e.g. particle swarm optimization) and in the form of Evolutionary Machine Learning approaches have been successfully applied to mitigate the problems that arise when training DGMs, leveraging the quality of the results to impressive levels. Among other approaches, these new solutions include LLM, GAN, VAE, AR, and DM training methods or fine tuning optimization based on evolutionary and coevolutionary algorithms, the combination of deep neuroevolution with training approaches, and the evolutionary exploration of latent space.
The workshop on Enhancing Generative Machine Learning with Evolutionary Computation (EGML-EC) aims to act as a medium for debate, exchange of knowledge and experience, and encourage collaboration for researchers focused on DGMs and the EC community. Bringing these two communities together will be essential for making significant advances in this research area. Thus, this workshop provides a critical forum for disseminating the experience on the topic of enhancing generative modelling with EC, presenting new and ongoing research in the field, and to attract new interest from our community.
Topics of Interest
Particular topics of interest are (not exclusively):
Evolutionary prompt optimization for large language models
Evolutionary operators based on large language models
Evolutionary and co-evolutionary algorithms to train deep generative models
EC-based optimization of hyper-parameters for deep generative models
Neuroevolution applied to train deep generative architectures
Dynamic EC-based evolution of deep generative models training parameters
Evolutionary latent space exploration (e.g. LVEs)
Real-world applications of EC-based deep generative models solutions
Multi-criteria adversarial training of deep generative models
Evolutionary generative adversarial learning models
Software libraries and frameworks for deep generative models applying EC
Submissions
We invite submissions of the following types of papers:
research papers (up to 8 pages)
position papers (up to 4 pages)
Accepted submissions will be presented during the workshop and will appear in the GECCO Companion ACM proceedings. Paper's format should follow the GECCO 2024 instructions.
Submissions of early and in-progress work are encouraged. Authors of accepted papers proposing novel software developments will be encouraged to give a demo or a short introductory tutorial. Authors of accepted papers describing novel software or technical developments will be encouraged to give a demonstration during the workshop.
Instructions
Submitted papers are required to be in compliance with the GECCO 2024 Papers Submission Instructions.
Workshop papers must be submitted using the GECCO submission site.
Important dates
Submission opening: February 12, 2024
Submission deadline: April 12 (FINAL), 2024
Acceptance notification: May 3, 2024
Camera-ready and registration: May 10, 2024
Workshop date: TBC depending on GECCO program schedule (July 14 or 18, 2024)