Fragment-Wise Interpretability in Graph Neural Networks via Molecule Decomposition and Contribution Analysis

• URL: http://arxiv.org/abs/2508.15015v1
• Date: Wed, 20 Aug 2025 19:15:53 GMT
• Title: Fragment-Wise Interpretability in Graph Neural Networks via Molecule Decomposition and Contribution Analysis
• Authors: Sebastian Musiał, Bartosz Zieliński, Tomasz Danel,
• Abstract summary: SEAL (Substructure Explanation via Attribution Learning) is a new interpretable graph neural network that attributes model predictions to meaningful molecular subgraphs.<n> SEAL decomposes input graphs into chemically relevant fragments and estimates their causal influence on the output.
• Score: 0.9217021281095907
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph neural networks have demonstrated remarkable success in predicting molecular properties by leveraging the rich structural information encoded in molecular graphs. However, their black-box nature reduces interpretability, which limits trust in their predictions for important applications such as drug discovery and materials design. Furthermore, existing explanation techniques often fail to reliably quantify the contribution of individual atoms or substructures due to the entangled message-passing dynamics. We introduce SEAL (Substructure Explanation via Attribution Learning), a new interpretable graph neural network that attributes model predictions to meaningful molecular subgraphs. SEAL decomposes input graphs into chemically relevant fragments and estimates their causal influence on the output. The strong alignment between fragment contributions and model predictions is achieved by explicitly reducing inter-fragment message passing in our proposed model architecture. Extensive evaluations on synthetic benchmarks and real-world molecular datasets demonstrate that SEAL outperforms other explainability methods in both quantitative attribution metrics and human-aligned interpretability. A user study further confirms that SEAL provides more intuitive and trustworthy explanations to domain experts. By bridging the gap between predictive performance and interpretability, SEAL offers a promising direction for more transparent and actionable molecular modeling.

Related papers

• Adaptive Substructure-Aware Expert Model for Molecular Property Prediction [5.087741013479207]
  Graph Neural Networks (GNNs) have shown promising results by modeling molecules as molecular graphs.<n>Existing methods often overlook the varying contributions of different substructures to molecular properties.<n>We propose Molecular-Mol, a novel GNN-based framework that leverages a Mixture-of-Experts (MoE) approach for molecular property prediction.
  arXiv  Detail & Related papers  (2025-04-08T09:25:03Z)
• I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data? [76.15163242945813]
  Large language models (LLMs) have led many to conclude that they exhibit a form of intelligence.<n>We introduce a novel generative model that generates tokens on the basis of human-interpretable concepts represented as latent discrete variables.
  arXiv  Detail & Related papers  (2025-03-12T01:21:17Z)
• Knowledge-aware contrastive heterogeneous molecular graph learning [77.94721384862699]
  We propose a paradigm shift by encoding molecular graphs into Heterogeneous Molecular Graph Learning (KCHML)<n>KCHML conceptualizes molecules through three distinct graph views-molecular, elemental, and pharmacological-enhanced by heterogeneous molecular graphs and a dual message-passing mechanism.<n>This design offers a comprehensive representation for property prediction, as well as for downstream tasks such as drug-drug interaction (DDI) prediction.
  arXiv  Detail & Related papers  (2025-02-17T11:53:58Z)
• Contrastive Dual-Interaction Graph Neural Network for Molecular Property Prediction [0.0]
  We introduce DIG-Mol, a novel self-supervised graph neural network framework for molecular property prediction. DIG-Mol integrates a momentum distillation network with two interconnected networks to efficiently improve molecular characterization. We have established DIG-Mol's state-of-the-art performance through extensive experimental evaluation in a variety of molecular property prediction tasks.
  arXiv  Detail & Related papers  (2024-05-04T10:09:27Z)
• Bi-level Contrastive Learning for Knowledge-Enhanced Molecule Representations [68.32093648671496]
  We introduce GODE, which accounts for the dual-level structure inherent in molecules.<n> Molecules possess an intrinsic graph structure and simultaneously function as nodes within a broader molecular knowledge graph.<n>By pre-training two GNNs on different graph structures, GODE effectively fuses molecular structures with their corresponding knowledge graph substructures.
  arXiv  Detail & Related papers  (2023-06-02T15:49:45Z)
• Atomic and Subgraph-aware Bilateral Aggregation for Molecular Representation Learning [57.670845619155195]
  We introduce a new model for molecular representation learning called the Atomic and Subgraph-aware Bilateral Aggregation (ASBA) ASBA addresses the limitations of previous atom-wise and subgraph-wise models by incorporating both types of information. Our method offers a more comprehensive way to learn representations for molecular property prediction and has broad potential in drug and material discovery applications.
  arXiv  Detail & Related papers  (2023-05-22T00:56:00Z)
• Enhancing Model Learning and Interpretation Using Multiple Molecular Graph Representations for Compound Property and Activity Prediction [0.0]
  This research introduces multiple molecular graph representations that incorporate higher-level information. It investigates their effects on model learning and interpretation from diverse perspectives. The results indicate that combining atom graph representation with reduced molecular graph representation can yield promising model performance.
  arXiv  Detail & Related papers  (2023-04-13T04:20:30Z)
• Graph neural networks for the prediction of molecular structure-property relationships [59.11160990637615]
  Graph neural networks (GNNs) are a novel machine learning method that directly work on the molecular graph. GNNs allow to learn properties in an end-to-end fashion, thereby avoiding the need for informative descriptors. We describe the fundamentals of GNNs and demonstrate the application of GNNs via two examples for molecular property prediction.
  arXiv  Detail & Related papers  (2022-07-25T11:30:44Z)
• MEG: Generating Molecular Counterfactual Explanations for Deep Graph Networks [11.291571222801027]
  We present a novel approach to tackle explainability of deep graph networks in the context of molecule property prediction t asks. We generate informative counterfactual explanations for a specific prediction under the form of (valid) compounds with high structural similarity and different predicted properties. We discuss the results showing how the model can convey non-ML experts with key insights into the learning model focus in the neighbourhood of a molecule.
  arXiv  Detail & Related papers  (2021-04-16T12:17:19Z)
• Multi-View Graph Neural Networks for Molecular Property Prediction [67.54644592806876]
  We present Multi-View Graph Neural Network (MV-GNN), a multi-view message passing architecture. In MV-GNN, we introduce a shared self-attentive readout component and disagreement loss to stabilize the training process. We further boost the expressive power of MV-GNN by proposing a cross-dependent message passing scheme.
  arXiv  Detail & Related papers  (2020-05-17T04:46:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.