Learning Semantics-aware Search Operators for Genetic Programming
This work addresses the challenge of inefficient search in program synthesis for researchers in evolutionary computation, though it is incremental as it builds on existing genetic programming techniques.
The authors tackled the problem of rugged fitness landscapes in genetic programming by proposing a semantics-aware search operator that guides search towards programs with high potential, even if current fitness is low, and demonstrated its superiority over conventional methods on symbolic regression benchmarks.
Fitness landscapes in test-based program synthesis are known to be extremely rugged, with even minimal modifications of programs often leading to fundamental changes in their behavior and, consequently, fitness values. Relying on fitness as the only guidance in iterative search algorithms like genetic programming is thus unnecessarily limiting, especially when combined with purely syntactic search operators that are agnostic about their impact on program behavior. In this study, we propose a semantics-aware search operator that steers the search towards candidate programs that are valuable not only actually (high fitness) but also only potentially, i.e. are likely to be turned into high-quality solutions even if their current fitness is low. The key component of the method is a graph neural network that learns to model the interactions between program instructions and processed data, and produces a saliency map over graph nodes that represents possible search decisions. When applied to a suite of symbolic regression benchmarks, the proposed method outperforms conventional tree-based genetic programming and the ablated variant of the method.