Growing Reservoirs with Developmental Graph Cellular Automata

Matias Barandiaran, James Stovold
8/11/2025
cs.NEcs.AI

No official code found. Best implementation: mbaranr/alife2025 (4 stars, MIT, last commit 2026-02-22).

Abstract

Developmental Graph Cellular Automata (DGCA) are a novel model for morphogenesis, capable of growing directed graphs from single-node seeds. In this paper, we show that DGCAs can be trained to grow reservoirs. Reservoirs are grown with two types of targets: task-driven (using the NARMA family of tasks) and task-independent (using reservoir metrics). Results show that DGCAs are able to grow into a variety of specialized, life-like structures capable of effectively solving benchmark tasks, statistically outperforming `typical' reservoirs on the same task. Overall, these lay the foundation for the development of DGCA systems that produce plastic reservoirs and for modeling functional, adaptive morphogenesis.

View on arXivView PDF

Code Implementations(1)

mbaranr/alife2025Community68%
MIT

Code for the paper “Growing Reservoirs with Developmental Graph Cellular Automata.”

42Shell, PythonMar 28, 20258 months agoMIT

Similar Papers

Engineering morphogenesis of cell clusters with differentiable programming

79% match1 repo132024

MorphGrower: A Synchronized Layer-by-layer Growing Approach for Plausible Neuronal Morphology Generation

78% match1 repo82024

Growing Artificial Neural Networks for Control: the Role of Neuronal Diversity

78% match2024

FINE: Factorizing Knowledge for Initialization of Variable-sized Diffusion Models

76% match2024

Efficient Training of Large Vision Models via Advanced Automated Progressive Learning

76% match2 repos252024

Multi-Plasticity Synergy with Adaptive Mechanism Assignment for Training Spiking Neural Networks

76% match2025

Cite this paper

@article{barandiaran2025growing,
  title  = {Growing Reservoirs with Developmental Graph Cellular Automata},
  author = {Matias Barandiaran and James Stovold},
  year   = {2025},
  eprint = {2508.08091},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2508.08091v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2508.08091.svg)](https://codeofpaper.com/paper/2508.08091)

Discussion