Graph Structure Learning With Automatic Search of Hyperparameters Based on Genetic Programming
Created by W.Langdon from
gp-bibliography.bib Revision:1.8344
- @Article{Wang:2024:TETCI,
-
author = "Pengda Wang and Mingjie Lu and Weiqing Yan and
Dong Yang and Zhaowei Liu",
-
title = "Graph Structure Learning With Automatic Search of
Hyperparameters Based on Genetic Programming",
-
journal = "IEEE Transactions on Emerging Topics in Computational
Intelligence",
-
year = "2024",
-
volume = "8",
-
number = "6",
-
pages = "4155--4164",
-
month = dec,
-
keywords = "genetic algorithms, genetic programming, Graph neural
networks, Statistics, Sociology, Noise measurement,
Optimisation, Hyperparameter optimisation, Graphical
models, hyperparameters optimisation, graph structure
learning, genetic model",
-
ISSN = "2471-285X",
-
DOI = "
doi:10.1109/TETCI.2024.3386833",
-
abstract = "Graph neural networks (GNNs) rely heavily on graph
structures and artificial hyperparameters, which may
increase computation and affect performance. Most GNNs
use original graphs, but the original graph data has
problems with noise and incomplete information, which
easily leads to poor GNN performance. For this kind of
problem, recent graph structure learning methods
consider how to generate graph structures containing
label information. The settings of some hyperparameters
will also affect the expression of the GNN model. This
paper proposes a genetic graph structure learning
method (Genetic-GSL). Different from the existing graph
structure learning methods, this paper not only
optimises the graph structure but also the
hyperparameters. Specifically, different graph
structures and different hyperparameters are used as
parents; the offspring are cross-mutated through the
parents; and then excellent offspring are selected
through evaluation to achieve dynamic fitting of the
graph structure and hyperparameters. Experiments show
that, compared with other methods, Genetic-GSL
basically improves the performance of node
classification tasks by 1.2percent. With the increase
in evolution algebra, Genetic-GSL has good performance
on node classification tasks and resistance to
adversarial attacks.",
-
notes = "Also known as \cite{10504544}
University of Science and Technology of China, Hefei,
Anhui, China",
- }
Genetic Programming entries for
Pengda Wang
Mingjie Lu
Weiqing Yan
Dong Yang
Zhaowei Liu
Citations