Accelerating evolutionary exploration through language model-based transfer learning

TL;DR

This paper introduces a transfer learning framework for gene expression programming in symbolic regression, leveraging NLP techniques to improve initial solutions and accelerate convergence in evolutionary algorithms.

Contribution

It presents a novel method combining transfer learning and NLP to enhance gene expression programming for symbolic regression tasks.

Findings

Transfer learning improves convergence speed.

Enhanced initial solutions lead to better optimization results.

Framework effective across diverse regression problems.

Abstract

Gene expression programming is an evolutionary optimization algorithm with the potential to generate interpretable and easily implementable equations for regression problems. Despite knowledge gained from previous optimizations being potentially available, the initial candidate solutions are typically generated randomly at the beginning and often only include features or terms based on preliminary user assumptions. This random initial guess, which lacks constraints on the search space, typically results in higher computational costs in the search for an optimal solution. Meanwhile, transfer learning, a technique to reuse parts of trained models, has been successfully applied to neural networks. However, no generalized strategy for its use exists for symbolic regression in the context of evolutionary algorithms. In this work, we propose an approach for integrating transfer learning with gene expression programming applied to symbolic regression. The constructed framework integrates Natural Language Processing techniques to discern correlations and recurring patterns from equations explored during previous optimizations. This integration facilitates the transfer of acquired knowledge from similar tasks to new ones. Through empirical evaluation of the extended framework across a range of univariate problems from an open database and from the field of computational fluid dynamics, our results affirm that initial solutions derived via a transfer learning mechanism enhance the algorithm's convergence rate towards improved solutions.