Call For Papers: Special Issue on the Emergence of Modularity and Self-Organization

 

AIMS AND SCOPE

Springer Link here

Modularity is a concept that is intuitively clear, yet it can be conceptually difficult to pin down because it appears in a multitude of forms in nature and technology. Thus, support for modularity is a central element in human attempts to build complex systems in general. Software would not scale without functions and objects, likewise electronic circuits and mechanical systems can only be constructed through extensive reuse of modules at different levels of selection. Viewed from this perspective, modules take the form of a `process view' in which the operation performed by each component remains consistent while the overall system complexity increases.

However, this need not be the only approach to defining modules. From a biological perspective, a structural view might imply that modules are components of a system with stronger connections, or components defined by more frequent (internal) interaction. Both process and structural views implicitly attempt to define modules in terms of the degree of autonomy versus integration. Another potentially important aspect of a module is how it contributes to the dynamics of the wider system's behaviour, and how its contribution may change over time. Moreover, modules might invoke other modules, or sequences of modules may be invoked depending on context, facilitating the interpretation of behaviours at steadily higher levels of abstraction. 

This special issue invites new perspectives on the role of modularity in addressing issues such as scalability, reuse, and co-design in evolvable machines. We are particularly interested in submissions that illustrate advances to: 

• Open ended development of hierarchical relationships between modules and/or 
• Modular self-organization and emergence to achieve specific functional properties and/or
• Biological underpinnings of modularity in digital evolution of computer programs/evolvable machines.

We invite authors to submit works that illustrate the impact of modularity and self-organization on the ability to discover genotype/phenotypes more efficiently or improve the efficiency of operation. To this end, ongoing themes include mechanisms by which communication, ensembles, and cellular automata enable modules to develop or interact. Another related topic is the role of modularity on improving interpretability, where specific decision-making processes might be associated with particular modules.

Environments that demonstrate the importance of modularity are also of interest and might include multi-task learning or situations in which catastrophic forgetting plays a role. 

We also invite submissions that illustrate how co-design or co-evolution may result in better use of modules, or to what degree decomposing a task facilitates the organization of behavioural properties through module reuse.

TOPICS OF INTEREST

Impact of modularity and self organization on:

• efficiency of operation
• compartmentalizing credit assignment such that only specific modules are refined / catastrophic forgetting is mitigated
• emergence of individual versus group behaviours and their co-ordination
• hierarchical relationships versus ensembles or teams, and major transitions
• generalization, robustness, and evolvability
• automatic feature selection, feature construction and/or interpretability
• hardware acceleration, microarchitectures, and cyber-physical systems

Role of task transfer, multi-task, or continuous learning on:

• self organization, complexity, and emergence of modularity
• organization and development of units of selection
• the co-design or co-evolution of effective modularity

The role of modularity on internal state and memory:

• distributed and/or shared memory versus individual internal state
• cycles of interaction between modules or internal / external state

IMPORTANT DATES

• Submission deadline: December 15, 2026
• Notification of first review: January 26, 2027
• Submission of revised manuscript: March 26, 2027
• Notification of final decision: April 26, 2027

GUEST EDITORS

• Stephen Kelly, McMaster University, Hamilton, Canada, spkelly@mcmaster.ca
• Malcolm Heywood, Dalhousie University, Halifax, Canada,  mheywood@dal.ca

Call For Papers: Special Issue on Lexicase Selection

AIMS AND SCOPE

Springer Link here 

Lexicase selection selects individuals on the basis of their performance on training cases that are considered one at a time, in random order. First developed for parent selection in genetic programming, it has since been applied in other settings both within evolutionary computation and in other forms of machine learning [1,2].

Lexicase selection has been used, for example, for software synthesis, evolutionary robotics, multiobjective optimization, reinforcement learning, learning classifier systems (with a variant called batch lexicase selection), symbolic regression (with a variant called epsilon lexicase selection) and deep learning (with a variant called gradient lexicase selection). It has been analyzed with respect to selection efficiency, population diversity, the promotion of specialists, and problem-solving power, and such analyses have given rise to new methods such as informed downsampled lexicase selection and probabilistic lexicase selection.

This special issue of GPEM will focus on further studies of lexicase selection, its applications, its variants, and its analysis. It aims to draw together ideas from various perspectives to give a more holistic view of lexicase selection, helping guide future research and practice, deepening our understanding of how and why it works and when it should and shouldn't be used.

[1] T. Helmuth, L. Spector and J. Matheson, "Solving Uncompromising Problems With Lexicase Selection," in IEEE Transactions on Evolutionary Computation, vol. 19, no. 5, pp. 630-643, Oct. 2015, doi: 10.1109/TEVC.2014.2362729 

[2] Spector, L., Ding, L., Boldi, R. (2024). Particularity. In: Winkler, S., Trujillo, L., Ofria, C., Hu, T. (eds) Genetic Programming Theory and Practice XX. Genetic and Evolutionary Computation. Springer, Singapore. https://doi.org/10.1007/978-981-99-8413-8_9 

TOPICS OF INTEREST

• Analysis of the benefits and drawbacks of lexicase selection
• Analysis of applications that are amenable (or not) to lexicase selection
• Studies of variants of lexicase selection
• Creation of new variants of lexicase selection
• Critiques or position papers considering lexicase selection
• The lexicase algorithm used beyond parent selection
• Lexicase selection in contexts beyond genetic programming, including but not limited to other evolutionary algorithms, evolutionary robotics, reinforcement learning, and neural networks

IMPORTANT DATES

• Submission deadline: November 30, 2026
• Notification of first review: January 15, 2027
• Submission of revised manuscript: March 15, 2027
• Notification of final decision: April 15, 202

GUEST EDITORS

• Thomas Helmuth, Hamilton College, Clinton, United States, thelmuth@hamilton.edu 
• Lee Spector,  Amherst College, Amherst Center, United States, lspector@amherst.edu 
• Edward Pantridge, Swoop Inc., United States,   eddie.pantridge@gmail.com