Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Musiał, Sebastian, Zieliński, Bartosz, Danel, Tomasz
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

PhAME: Phenotype-Aware Molecular Editing via Latent Diffusion
by: Janisiów, Łukasz, et al.
Published: (2026)

SONG: Self-Organizing Neural Graphs
by: Struski, Łukasz, et al.
Published: (2021)

Enhancing Chemical Explainability Through Counterfactual Masking
by: Janisiów, Łukasz, et al.
Published: (2025)

B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data
by: Proszewska, Magdalena, et al.
Published: (2025)

Causal Interpretation of Neural Network Computations with Contribution Decomposition
by: Melander, Joshua Brendan, et al.
Published: (2026)

How Interpretable Are Interpretable Graph Neural Networks?
by: Chen, Yongqiang, et al.
Published: (2024)

Efficient Multi-Source Knowledge Transfer by Model Merging
by: Osial, Marcin, et al.
Published: (2025)

OMENN: One Matrix to Explain Neural Networks
by: Wróbel, Adam, et al.
Published: (2024)

Sparse Decomposition of Graph Neural Networks
by: Hu, Yaochen, et al.
Published: (2024)

Molecule Generation with Fragment Retrieval Augmentation
by: Lee, Seul, et al.
Published: (2024)

Divide and not forget: Ensemble of selectively trained experts in Continual Learning
by: Rypeść, Grzegorz, et al.
Published: (2024)

Efficient Relation-aware Neighborhood Aggregation in Graph Neural Networks via Tensor Decomposition
by: Baghershahi, Peyman, et al.
Published: (2022)

LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision
by: Pach, Mateusz, et al.
Published: (2024)

Faithful Interpretation for Graph Neural Networks
by: Hu, Lijie, et al.
Published: (2024)

When Graph Neural Networks Meet Dynamic Mode Decomposition
by: Shi, Dai, et al.
Published: (2024)

This looks like what? Challenges and Future Research Directions for Part-Prototype Models
by: Elhadri, Khawla, et al.
Published: (2025)

Framework GNN-AID: Graph Neural Network Analysis Interpretation and Defense
by: Lukyanov, Kirill, et al.
Published: (2025)

Interpreting Temporal Graph Neural Networks with Koopman Theory
by: Guerra, Michele, et al.
Published: (2024)

Interpretable Graph Neural Networks for Heterogeneous Tabular Data
by: Alkhatib, Amr, et al.
Published: (2024)

Graph Structure Learning with Interpretable Bayesian Neural Networks
by: Wasserman, Max, et al.
Published: (2024)

Factor Graph-based Interpretable Neural Networks
by: Li, Yicong, et al.
Published: (2025)

Interpretable Graph Neural Networks for Tabular Data
by: Alkhatib, Amr, et al.
Published: (2023)

The Interpretable and Effective Graph Neural Additive Networks
by: Bechler-Speicher, Maya, et al.
Published: (2024)

DAVE: Distribution-aware Attribution via ViT Gradient Decomposition
by: Wróbel, Adam, et al.
Published: (2026)

GIN-Graph: A Generative Interpretation Network for Model-Level Explanation of Graph Neural Networks
by: Yue, Xiao, et al.
Published: (2025)

Hierarchical Frequency-Decomposition Graph Neural Networks for Road Network Representation Learning
by: Ma, Jingtian, et al.
Published: (2025)

Local Fragments, Global Gains: Subgraph Counting using Graph Neural Networks
by: Roy, Shubhajit, et al.
Published: (2023)

On Stealing Graph Neural Network Models
by: Podhajski, Marcin, et al.
Published: (2025)

Zero-Shot Neural Network Evaluation with Sample-Wise Activation Patterns
by: Peng, Yameng, et al.
Published: (2026)

Edge-Wise Graph-Instructed Neural Networks
by: Della Santa, Francesco, et al.
Published: (2024)

Closed-Form Interpretation of Neural Network Classifiers with Symbolic Gradients
by: Wetzel, Sebastian Johann
Published: (2024)

GoMS: Graph of Molecule Substructure Network for Molecule Property Prediction
by: Qu, Shuhui, et al.
Published: (2025)

From GNNs to Trees: Multi-Granular Interpretability for Graph Neural Networks
by: Yang, Jie, et al.
Published: (2025)

A Generalized Tikhonov Layer for Interpretable-by-design Graph Neural Networks
by: Tremblay, Nicolas, et al.
Published: (2026)

Interpretability of Graph Neural Networks to Assess Effects of Global Change Drivers on Ecological Networks
by: Anakok, Emre, et al.
Published: (2025)

GemNet: Universal Directional Graph Neural Networks for Molecules
by: Gasteiger, Johannes, et al.
Published: (2021)

Fragmentation is Efficiently Learnable by Quantum Neural Networks
by: Mints, Mikhail, et al.
Published: (2025)

Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck
by: Hoang, Van Thuy, et al.
Published: (2024)

Efficient Model-Stealing Attacks Against Inductive Graph Neural Networks
by: Podhajski, Marcin, et al.
Published: (2024)

Sparse Explanations of Neural Networks Using Pruned Layer-Wise Relevance Propagation
by: Sarmiento, Paulo Yanez, et al.
Published: (2024)