[hpc-announce] [Last CfP] EGML-EC GECCO 2024 workshop on Enhancing Generative Machine Learning with Evolutionary Computation

[Jamal Toutouh]

CALL FOR PAPERS

EGML-EC at GECCO-2024

3rd Workshop on Enhancing Generative Machine Learning with Evolutionary
Computation

https://urldefense.us/v3/__https://sites.google.com/view/egml-ec2024__;!!G_uCfscf7eWS!afmLVgIfjv6eiCYImm_b63sMCDLU001dKyg2q--m09BMapVjQPjcdAkkW9st787vTOjBKOojzOXzfamxR7r4Jtdm18l6$ 

Genetic and Evolutionary Computation Conference (GECCO'24)

Melbourne, Australia (hybrid), July 14 to 18, 2024

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 SD 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



All accepted papers of this workshop will be included in the Proceedings of
the Genetic and Evolutionary Computation Conference (GECCO'24) Companion
Volume.



Important dates

Submission opening: February 12, 2024

Submission deadline: *April 8, 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)

There will be NO EXTENSIONS to any of the deadlines



Instructions for Authors

We invite submissions of two types of paper:

   -

   Regular papers (limit 8 pages)
   -

   Short papers (limit 4 pages)

Papers should present original work that meets the high-quality standards
of GECCO. Each paper will be rigorously evaluated in a review process.
Accepted papers appear in the ACM digital library as part of the Companion
Proceedings of GECCO. Each paper accepted needs to have at least one author
registered by the author registration deadline. Papers must be submitted
via the online submission system
https://urldefense.us/v3/__https://ssl.linklings.net/conferences/gecco/__;!!G_uCfscf7eWS!afmLVgIfjv6eiCYImm_b63sMCDLU001dKyg2q--m09BMapVjQPjcdAkkW9st787vTOjBKOojzOXzfamxR7r4JuB-LCCO$ . Please refer to
https://urldefense.us/v3/__https://gecco-2024.sigevo.org/Paper-Submission-Instructions__;!!G_uCfscf7eWS!afmLVgIfjv6eiCYImm_b63sMCDLU001dKyg2q--m09BMapVjQPjcdAkkW9st787vTOjBKOojzOXzfamxR7r4JuxqTxMe$  for more
detailed instructions.

As a published ACM author, you and your co-authors are subject to all ACM
Publications Policies (https://urldefense.us/v3/__https://www.acm.org/publications/policies/toc__;!!G_uCfscf7eWS!afmLVgIfjv6eiCYImm_b63sMCDLU001dKyg2q--m09BMapVjQPjcdAkkW9st787vTOjBKOojzOXzfamxR7r4JiVXCai0$ ),
including ACM's new Publications Policy on Research Involving Human
Participants and Subjects (
https://urldefense.us/v3/__https://www.acm.org/publications/policies/research-involving-human-participants-and-subjects__;!!G_uCfscf7eWS!afmLVgIfjv6eiCYImm_b63sMCDLU001dKyg2q--m09BMapVjQPjcdAkkW9st787vTOjBKOojzOXzfamxR7r4Jj6emGL7$ 
).



Workshop Chairs

   -

   Jamal Toutouh, Univ. of Málaga (ES) - MIT (USA), jamal at uma.es
   -

   Una-May O’Reilly, MIT (USA), unamay at csail.mit.edu
   -

   João Correia, University of Coimbra (PT), jncor at dei.uc.pt
   -

   Penousal Machado, University of Coimbra (PT), machado at dei.uc.pt
   -

   Erik Hemberg,  MIT (USA), hembergerik at csail.mit.edu


More information at <https://urldefense.us/v3/__https://sites.google.com/view/egml-ec-2023__;!!G_uCfscf7eWS!afmLVgIfjv6eiCYImm_b63sMCDLU001dKyg2q--m09BMapVjQPjcdAkkW9st787vTOjBKOojzOXzfamxR7r4Jt20tZxn$ >
https://urldefense.us/v3/__https://sites.google.com/view/egml-ec2024__;!!G_uCfscf7eWS!afmLVgIfjv6eiCYImm_b63sMCDLU001dKyg2q--m09BMapVjQPjcdAkkW9st787vTOjBKOojzOXzfamxR7r4Jtdm18l6$ 

-- 
Jamal Toutouh El Alamin

-- 
Jamal Toutouh El Alamin