https://doi.org/10.1140/epjp/s13360-025-06804-0
Regular Article
Temperature-based pruning for input features in Graph Neural Networks
1
Department of Physics and Astronomy, University of Bologna, Bologna, Italy
2
Department of Chemical and Geological Sciences, University of Modena and Reggio Emilia, Modena, Italy
3
Department of Pharmacy and Biotechnologies, University of Bologna, Bologna, Italy
4
Federal Institute For Materials Research and Testing, BAM, Berlin, Germany
5
Institute of Physics and Astronomy, University of Potsdam, Potsdam, Germany
a
This email address is being protected from spambots. You need JavaScript enabled to view it.
Received:
13
January
2025
Accepted:
26
August
2025
Published online:
13
September
2025
In the present work, we employ the concept of neural network temperature to prune unimportant features in input to a Graph Neural Network (GNN) architecture. In benchmark datasets for node and graph property prediction, each node comes equipped with a vector of numerous features. It is paramount to understand which information is actually necessary and which can be discarded, both for efficiency and explainability. The temperature is linked to the gradient activity due to the loss function minimization and leads to pruning of weight structures associated with small gradients. This study is done on different GNN architectures, one for node classification and another one for link prediction, and several benchmark datasets are employed. We compare the results with similar experiments previously conducted on the filters of Convolutional Neural Networks. Although still at the proof-of-concept stage, our temperature-based pruning technique stands as a promising alternative to state-of-the-art magnitude-based pruning techniques.
© The Author(s) 2025
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
