Evolutionary Computation and Advanced Network Inference for Complex Systems Modeling

Dear Colleagues,

Complex systems across science and engineering are characterized by non-linear dynamics, high dimensionality, and intricate, often hidden, inter-component dependencies. Traditional modeling methods often fall short in characterizing the dynamic, directional, and context-specific interactions that truly govern these systems.

This Special Issue invites novel research that harnesses the power of Evolutionary Computation (EC) and Advanced Network Inference to address these fundamental challenges. The specific promise of this synergy lies where traditional methods struggle. While powerful, approaches like Bayesian learning can become computationally intractable in high-dimensional systesystemsms, and methods like symbolic regression or gradient-based optimization can be trapped by non-convex or non-differentiable search spaces. EC techniques (e.g., genetic algorithms, neuroevolution, genetic programming) provide a robust, gradient-free global search capability. We specifically seek contributions that leverage EC to tackle the most difficult aspects of modern inference: discovering optimal network topologies, calibrating large-scale dynamic models (e.g., systems of differential equations), or optimizing the complex architectures of deep learning models (e.g., GNNs) used for system representation.

We seek contributions that advance the theoretical foundations of these synergistic methods or demonstrate their efficacy in unraveling the internal workings of complex systems.

Topics of interest include, but are not limited to, the following:

• Methodological Innovations and Theoretical Foundations: Novel EC-based approaches and hybrid metaheuristics for network structure learning, parameter optimization, feature selection, and dynamic system calibration.
• Intersections with Deep Learning and AI Systems: Applications of EC in Neural Architecture Search (NAS) for time-series or graph data, optimization of Graph Neural Networks (GNNs), and the development of Evolutionary Reinforcement Learning (ERL) frameworks for complex systems.
• Specific, Problem-Oriented Applications: We encourage submissions that demonstrate efficacy on specific, challenging problems, such as the following:
  • Discovering gene regulatory or metabolic networks from sparse, noisy time-series data.
  • Modeling systemic risk propagation or evolving agent-based models for financial market stability.
  • Optimizing network-level control policies for smart transportation grids or resilient supply chains.
• Reproducibility, Sustainability, and Open Science: In recognition of the computational demands of these methods, we invite research on computationally efficient, resource efficient, or scalable algorithms. Furthermore, submissions that include publicly available code, datasets, and benchmarks to ensure scientific reproducibility are strongly encouraged.

Dr. Miao He
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.