Data Types as a More Ergonomic Frontend for Grammar-Guided Genetic Programming

Espada, Guilherme; Ingelse, Leon; Canelas, Paulo; Barbosa, Pedro; Fonseca, Alcides

doi:10.1145/3564719.3568697

Cited by 7 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the implementation of the experiments, we used GeneticEngine [22], a GGGP framework in Python that supports the three GGGP approaches presented in Section 2. GeneticEngine uses the same tree-generation method for each algorithm, diminishing performance differences due to implementation.…”

Section: Methodsmentioning

confidence: 99%

A Comparison of Representations in Grammar-Guided Genetic Programming in the context of Glucose Prediction in People with Diabetes

Ingelse,

Hidalgo,

Colmenar

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

The representation of individuals in Genetic Programming (GP) has a large impact on the evolutionary process. In this work, we investigate the evolutionary process of three Grammar-Guided GP (GGGP) methods, Context-Free Grammars GP (CFG-GP), Grammatical Evolution (GE) and Structured Grammatical Evolution (SGE), in the context of the complex, real-world problem of predicting the glucose level of people with diabetes two hours ahead of time.Our analysis differs from previous analyses by (1) comparing all three methods on a complex benchmark, (2) implementing the methods in the same framework, allowing a fairer comparison, and (3) analyzing the evolutionary process outside of performance.We conclude that representation choice is more impactful with a higher maximum depth, and that CFG-GP better explores the search space for deeper trees, achieving better results. Furthermore, we find that CFG-GP relies more on feature construction, whereas GE and SGE rely more on feature selection.Additionally, we altered the GGGP methods in two ways: using $\epsilon$-lexicase selection, which solved the overfitting problem of CFG-GP; and with a penalization of complex trees, to create more interpretable trees. Combining $\epsilon$-lexicase selection with CFG-GP performed best.Finally, we evaluated the impact of initialization methods in the quality of solutions, having found that they have no impact, even when the change of representation has.

show abstract

Section: Methodsmentioning

confidence: 99%

A Comparison of Representations in Grammar-Guided Genetic Programming in the context of Glucose Prediction in People with Diabetes

Ingelse,

Hidalgo,

Colmenar

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…We devised a perturbation grammar to constrain the perturbations to be biologically plausible. Using Grammar-Guided Genetic Programming (GGGP) [58], extended with meta-handlers [16], both the population initialization and genetic operators modify the representation of individuals within these constraints.…”

Section: Representationmentioning

confidence: 99%

“…We use standard tree-based GGGP mutation and crossovers, extended with meta-handlers [16]. In a typical GGGP mutation, a mutation at a given position of the list would generate random, new elements for the remainder of the list.…”

Section: Genetic Operatorsmentioning

confidence: 99%

“…Our approach and the baseline were implemented on top of Ge-neticEngine v0.8.5 [16], which supports meta-handlers that allow encoding constraints on the perturbations. Specifically, we developed Deep learning based Resource for Exploring Splicing Signatures (DRESS) v0.0.1 (https://github.com/PedroBarbosa/dress), which incorporates the proposed techniques (see Supplementary Information for details).…”

Section: Experimental Settingsmentioning

confidence: 99%

See 1 more Smart Citation

Semantically Rich Local Dataset Generation for Explainable AI in Genomics

Barbosa,

Savisaar,

Fonseca

2024

Proceedings of the Genetic and Evolutionary Computation Conference

Self Cite

View full text Add to dashboard Cite

Black box deep learning models trained on genomic sequences excel at predicting the outcomes of different gene regulatory mechanisms. Therefore, interpreting these models may provide novel insights into the underlying biology, supporting downstream biomedical applications. Due to their complexity, interpretable surrogate models can only be built for local explanations (e.g., a single instance). However, accomplishing this requires generating a dataset in the neighborhood of the input, which must maintain syntactic similarity to the original data while introducing semantic variability in the model's predictions. This task is challenging due to the complex sequence-to-function relationship of DNA.We propose using Genetic Programming to generate datasets by evolving perturbations in sequences that contribute to their semantic diversity. Our custom, domain-guided individual representation effectively constrains syntactic similarity, and we provide two alternative fitness functions that promote diversity with no computational effort. Applied to the RNA splicing domain, our approach quickly achieves good diversity and significantly outperforms a random baseline in exploring the search space, as shown by our proof-of-concept, short RNA sequence. Furthermore, we assess its generalizability and demonstrate scalability to larger sequences, resulting in a ≈30% improvement over the baseline. CCS CONCEPTS• Computing methodologies → Genetic programming.

show abstract

Domain-Aware Feature Learning with Grammar-Guided Genetic Programming

Ingelse¹,

Fonseca²

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Data Types as a More Ergonomic Frontend for Grammar-Guided Genetic Programming

Cited by 7 publications

References 25 publications

A Comparison of Representations in Grammar-Guided Genetic Programming in the context of Glucose Prediction in People with Diabetes

A Comparison of Representations in Grammar-Guided Genetic Programming in the context of Glucose Prediction in People with Diabetes

Semantically Rich Local Dataset Generation for Explainable AI in Genomics

Domain-Aware Feature Learning with Grammar-Guided Genetic Programming

Contact Info

Product

Resources

About