Bootstrapping OTS-Funcimg Pre-training Model (Botfip) -- A Comprehensive Symbolic Regression Framework

TL;DR

This paper introduces Botfip, a novel multimodal framework for symbolic regression in scientific computing, inspired by image-text models, demonstrating advantages in low-complexity problems and promising broader applications.

Contribution

The paper proposes Botfip, a new multimodal pre-training model for symbolic regression that leverages function images and operation tree sequences, inspired by image-text frameworks.

Findings

Botfip shows improved performance in low-complexity symbolic regression tasks.

The framework demonstrates potential for broader scientific computing applications.

Botfip offers a new perspective on multimodal data mining in AI for science.

Abstract

In the field of scientific computing, many problem-solving approaches tend to focus only on the process and final outcome, even in AI for science, there is a lack of deep multimodal information mining behind the data, missing a multimodal framework akin to that in the image-text domain. In this paper, we take Symbolic Regression(SR) as our focal point and, drawing inspiration from the BLIP model in the image-text domain, propose a scientific computing multimodal framework based on Function Images (Funcimg) and Operation Tree Sequence (OTS), named Bootstrapping OTS-Funcimg Pre-training Model (Botfip). In SR experiments, we validate the advantages of Botfip in low-complexity SR problems, showcasing its potential. As a MED framework, Botfip holds promise for future applications in a broader range of scientific computing problems.