[GECCO CFP] Call for Papers - International Workshop on Evolutionary Rule-based Machine Learning (ERBML 2023, formerly IWLCS) as part of GECCO 2023

[Abubakar Siddique]

Dear Colleagues,


The 26th International Workshop on Evolutionary Rule-based Machine Learning (ERBML 2023, formerly IWLCS) will be held as part of the Genetic and Evolutionary Computation Conference (GECCO 2023, http://gecco-2023.sigevo.org/ ) which will take place from 15 to 19 July 2023 in Lisbon, Portugal (with all events facilitating online participation).


Submission deadline: 14 April 2023


For more information and updates, visit https://iwlcs.organic-computing.de



*AIMS AND SCOPE*


Evolutionary rule-based machine learning (ERBML) is a family of machine learning (ML) methods that leverage the strengths of metaheuristics to find an optimal set of rules to make decisions. There are ERBML methods for solving supervised, unsupervised as well as reinforcement learning tasks. The most prominent ERBML methods include Learning Classifier Systems, Ant-Miner, Artificial Immune Systems as well as evolving fuzzy rule-based systems.

Rules in ERBML are IF-THEN statements: They include some sort of restriction of the input space (IF) that maps inputs to whether the rule \emph{matches} them. The second part of a rule (THEN) is a submodel which is fit to the inputs that the rule matches. At that, submodels may range from simple constant or linear models to more sophisticated ones such as neural networks or genetic programming trees. Metaheuristics used in ERBML include evolutionary, symbolic as well as swarm-based methods. They typically optimize the rules' placement (i.e. their IF-parts) since the submodels are often straightforward to fit.

The key feature of the models built is an inherent comprehensibility (explainability, transparency, interpretability), a property becoming a matter of high interest for many ML communities recently as part of the eXplainable AI (XAI) movement. The particular topics of interest of this workshop are (not exclusively):

- Advances in ERBML methods (local models, problem space partitioning, rule mixing, …)

- Applications of ERBML (medical domains, bioinformatics, computer vision, games, cyber-physical systems, …)

- State-of-the-art analysis (surveys, sound comparative experimental benchmarks, carefully crafted reproducibility studies, …)

- Formal developments in ERBML (provably optimal parametrization, time bounds, generalization, …)

- Comprehensibility of evolved rule sets (knowledge extraction, visualization, interpretation of decisions, XAI, …)

- Advances in ERBML paradigms (Michigan/Pittsburgh style, hybrids, iterative rule learning, …)

- Hyperparameter optimization for ERBML (hyperparameter selection, online self-adaptation, …)

- Optimizations and parallel implementations (GPU acceleration, matching algorithms, …)


*KEY DATES*


- Submission deadline: 14 April 2023

- Decision notification: 3 May 2023

- Camera-ready deadline: 10 May 2023


*SUBMISSIONS*


This workshop accepts two types of submissions:

- Regular papers (up to 8 pages excluding references) that report on innovative ideas and novel research results around the topic of Evolutionary Rule-based Machine Learning (ERBML). Reported results and findings have to be integrated with the current state of the art and should provide details and metrics allowing for an assessment of practical as well as statistical significance.

- Extended abstracts (up to  2 pages excluding references) summarizing, showcasing and/or highlighting your recent, already-published, work on ERBML


Furthermore, submissions must

- conform to the GECCO submission instructions which can be found at https://gecco-2022.sigevo.org/Paper-Submission-Instructions .

- not exceed *8 pages*, excluding references.

- be submitted via GECCO’s submission system at https://ssl.linklings.net/conferences/gecco/ .


*WORKSHOP ORGANIZATION*


- David Pätzel, University of Augsburg, Germany

- Alexander Wagner, University of Hohenheim, Germany

- Michael Heider, University of Augsburg, Germany

- Abubakar Siddique, Wellington Institute of Technology, Te Pūkenga – Whitireia WelTec, New Zealand


*PRELIMINARY PROGRAM COMMITTEE*


Jaume Bacardit, Lashon B. Booker, Will N. Browne, Larry Bull, Ali Hamzeh, Michael Heider, Luis Miramontes Hercog, Muhammad Iqbal, Karthik Kuber, Pier Luca Lanzi, Daniele Loiacono, Masaya Nakata, Yusuke Nojima, David Pätzel, Sonia Schulenburg, Kamran Shafi, Shinichi Shirakawa, Abubakar Siddique, Anthony Stein, Wolfgang Stolzmann, Ryan J. Urbanowicz, Danilo V. Vargas, Alexander Wagner, Stewart W. Wilson


-------------------------

As a published ACM author, you and your co-authors are subject to all ACM Publications Policies (https://www.acm.org/publications/policies/toc), including ACM's new Publications Policy on Research Involving Human Participants and Subjects (https://www.acm.org/publications/policies/research-involving-human-participants-and-subjects).


Dr. Abubakar Siddique He/Him
Lecturer
School of Innovation, Design and Technology
Wellington Institute of Technology
Te Pūkenga – Whitireia WelTec
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://gecco.linklings.com/pipermail/callforpapers_gecco.linklings.com/attachments/20230404/7dd18ee1/attachment.html>