RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanation

Jingxiang Qu, Wenhan Gao, Jiaxing Zhang, Xufeng Liu, Hua Wei, Haibin Ling, Yi Liu
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50744-50761, 2025.

Abstract

3D Geometric Graph Neural Networks (GNNs) have emerged as transformative tools for modeling molecular data. Despite their predictive power, these models often suffer from limited interpretability, raising concerns for scientific applications that require reliable and transparent insights. While existing methods have primarily focused on explaining molecular substructures in 2D GNNs, the transition to 3D GNNs introduces unique challenges, such as handling the implicit dense edge structures created by a cutoff radius. To tackle this, we introduce a novel explanation method specifically designed for 3D GNNs, which localizes the explanation to the immediate neighborhood of each node within the 3D space. Each node is assigned an radius of influence, defining the localized region within which message passing captures spatial and structural interactions crucial for the model’s predictions. This method leverages the spatial and geometric characteristics inherent in 3D graphs. By constraining the subgraph to a localized radius of influence, the approach not only enhances interpretability but also aligns with the physical and structural dependencies typical of 3D graph applications, such as molecular learning.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-qu25a, title = {{RISE}: Radius of Influence based Subgraph Extraction for 3{D} Molecular Graph Explanation}, author = {Qu, Jingxiang and Gao, Wenhan and Zhang, Jiaxing and Liu, Xufeng and Wei, Hua and Ling, Haibin and Liu, Yi}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {50744--50761}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/qu25a/qu25a.pdf}, url = {https://proceedings.mlr.press/v267/qu25a.html}, abstract = {3D Geometric Graph Neural Networks (GNNs) have emerged as transformative tools for modeling molecular data. Despite their predictive power, these models often suffer from limited interpretability, raising concerns for scientific applications that require reliable and transparent insights. While existing methods have primarily focused on explaining molecular substructures in 2D GNNs, the transition to 3D GNNs introduces unique challenges, such as handling the implicit dense edge structures created by a cutoff radius. To tackle this, we introduce a novel explanation method specifically designed for 3D GNNs, which localizes the explanation to the immediate neighborhood of each node within the 3D space. Each node is assigned an radius of influence, defining the localized region within which message passing captures spatial and structural interactions crucial for the model’s predictions. This method leverages the spatial and geometric characteristics inherent in 3D graphs. By constraining the subgraph to a localized radius of influence, the approach not only enhances interpretability but also aligns with the physical and structural dependencies typical of 3D graph applications, such as molecular learning.} }
Endnote
%0 Conference Paper %T RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanation %A Jingxiang Qu %A Wenhan Gao %A Jiaxing Zhang %A Xufeng Liu %A Hua Wei %A Haibin Ling %A Yi Liu %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-qu25a %I PMLR %P 50744--50761 %U https://proceedings.mlr.press/v267/qu25a.html %V 267 %X 3D Geometric Graph Neural Networks (GNNs) have emerged as transformative tools for modeling molecular data. Despite their predictive power, these models often suffer from limited interpretability, raising concerns for scientific applications that require reliable and transparent insights. While existing methods have primarily focused on explaining molecular substructures in 2D GNNs, the transition to 3D GNNs introduces unique challenges, such as handling the implicit dense edge structures created by a cutoff radius. To tackle this, we introduce a novel explanation method specifically designed for 3D GNNs, which localizes the explanation to the immediate neighborhood of each node within the 3D space. Each node is assigned an radius of influence, defining the localized region within which message passing captures spatial and structural interactions crucial for the model’s predictions. This method leverages the spatial and geometric characteristics inherent in 3D graphs. By constraining the subgraph to a localized radius of influence, the approach not only enhances interpretability but also aligns with the physical and structural dependencies typical of 3D graph applications, such as molecular learning.
APA
Qu, J., Gao, W., Zhang, J., Liu, X., Wei, H., Ling, H. & Liu, Y.. (2025). RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanation. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:50744-50761 Available from https://proceedings.mlr.press/v267/qu25a.html.

Related Material