An Analysis of the Ingredients for Learning Interpretable Symbolic Regression Models with Human-in-the-loop and Genetic Programming
Created by W.Langdon from
gp-bibliography.bib Revision:1.7970
- @Article{nadizar:2024:TELO,
-
author = "Giorgia Nadizar and Luigi Rovito and
Andrea {De Lorenzo} and Eric Medvet and Marco Virgolin",
-
title = "An Analysis of the Ingredients for Learning
Interpretable Symbolic Regression Models with
Human-in-the-loop and Genetic Programming",
-
journal = "ACM Transactions on Evolutionary Learning and
Optimization",
-
year = "2024",
-
volume = "4",
-
number = "1",
-
articleno = "5",
-
month = mar,
-
note = "17000th GP entry",
-
keywords = "genetic algorithms, genetic programming, Explainable
artificial intelligence, XAI, interpretable machine
learning, active learning, neural networks, ANN, deep
learning, evolutionary computation, evolutionary
algorithms, explainable evolutionary computation",
-
ISSN = "2688-299X",
-
publisher = "Association for Computing Machinery",
-
address = "New York, NY, USA",
-
URL = "https://doi.org/10.1145/3643688",
-
DOI = "doi:10.1145/3643688",
-
size = "30 pages",
-
abstract = "Interpretability is a critical aspect to ensure a fair
and responsible use of machine learning (ML) in
high-stakes applications. Genetic programming (GP) has
been used to obtain interpretable ML models because it
operates at the level of functional building blocks: if
these building blocks are interpretable, there is a
chance that their composition (i.e., the entire ML
model) is also interpretable. However, the degree to
which a model is interpretable depends on the observer.
Motivated by this, we study a recently-introduced
human-in-the-loop system that allows the user to steer
GPs generation process to their preferences, which
shall be online-learned by an artificial neural network
(ANN). We focus on the generation of ML models as
analytical functions (i.e., symbolic regression) as
this is a key problem in interpretable ML, and propose
a two-fold contribution. First, we devise more general
representations for the ML models for the ANN to learn
upon, to enable the application of the system to a
wider range of problems. Second, we delve into a deeper
analysis of the system’s components. To this end, we
propose an incremental experimental evaluation, aimed
at (1) studying the effectiveness by which an ANN can
capture the perceived interpretability for simulated
users, (2) investigating how the GP outcome is affected
across different simulated user feedback profiles, and
(3) determining whether humans participants would
prefer models that were generated with or without their
involvement. Our results pose clarity on pros and cons
of using a human-in-the-loop approach to discover
interpretable ML models with GP.",
-
notes = "https://dlnext.acm.org/journal/telo",
- }
Genetic Programming entries for
Giorgia Nadizar
Luigi Rovito
Andrea De Lorenzo
Eric Medvet
Marco Virgolin
Citations