A Probabilistic L-System Inspired Designer for Neural Architecture Search: A Graph Neural Network Case Study on Node Classification

Abstract

Designing graph neural networks (GNNs) for node classification still involves many manual choices. We study a probabilistic L-system-inspired encoding for architecture search, where each individual is a small set of production rules and repeated rewriting generates a symbol sequence that is translated into a GNN. Instead of evolving a fixed layer sequence directly, evolution optimizes the rule contents, their probabilities, the rewriting depth, and a few global architectural parameters. The derived sequences may contain graph message-passing operators, normalization, activation, dropout, and structural components such as Jumping Knowledge. We evaluate the method on nine node-classification benchmarks under multiple search settings that vary selection, crossover, and mutation. The results show that a compact rule-based representation can discover competitive architectures across different graph types while keeping the final model easy to inspect at the rule level.