A Hierarchical Multiview Symbolic Regression Method                  for Decoding Oceanic Metabolism 
Created by W.Langdon from
gp-bibliography.bib Revision:1.8612
- @InProceedings{lira:2025:GECCOcomp,
- 
  author =       "Hernan Lira and Luis Marti and Nayat Sanchez-Pi",
- 
  title =        "A Hierarchical Multiview Symbolic Regression Method
for Decoding Oceanic Metabolism",
- 
  booktitle =    "Symbolic Regression",
- 
  year =         "2025",
- 
  editor =       "Gabriel Kronberger and 
Fabricio {Olivetti de Franca} William {La Cava} and Steven Gustafson",
- 
  pages =        "2539--2547",
- 
  address =      "Malaga, Spain",
- 
  series =       "GECCO '25 Companion",
- 
  month =        "14-18 " # jul,
- 
  organisation = "SIGEVO",
- 
  publisher =    "Association for Computing Machinery",
- 
  publisher_address = "New York, NY, USA",
- 
  keywords =     "genetic algorithms, genetic programming, symbolic
regression, metabolic functions, metabolic pathways",
- 
  isbn13 =       "979-8-4007-1464-1",
- 
  URL =          " https://doi.org/10.1145/3712255.3734346", https://doi.org/10.1145/3712255.3734346",
- 
  DOI =          " 10.1145/3712255.3734346", 10.1145/3712255.3734346",
- 
  size =         "9 pages",
- 
  abstract =     "We introduce Hierarchical Multi-view Symbolic
Regression (H-MvSR), a novel evolutionary framework
that discovers closed-form expressions linking
environmental drivers to functional gene abundances
across multiple ocean layers. Our method models each
depth layer as a separate view while enforcing
hierarchical constraints that promote both global
structural consistency and local biological
specificity. The symbolic models are evolved under
multi-objective criteria that balance predictive
accuracy, expression simplicity, and cross-view
coherence. Furthermore, the framework incorporates
pathway-level biological priors, enabling grouped
symbolic modeling of molecular functions participating
in the same metabolic process. We evaluate H-MvSR using
depth-resolved genomic and environmental data from
global ocean expeditions and compare its performance
against state-of-the-art SR systems. Results show that
H-MvSR improves interpretability and multiview
consistency while recovering biologically meaningful
relationships.",
- 
  notes =        "GECCO-2025 SymReg workshop A Recombination of the 34th
International Conference on Genetic Algorithms (ICGA)
and the 30th Annual Genetic Programming Conference
(GP)",
- }
Genetic Programming entries for 
Hernan Lira
Luis Marti
Nayat Sanchez-Pi
Citations
