GnnXemplar: Exemplars to Explanations -- Natural Language Rules for Global GNN Interpretability

• URL: http://arxiv.org/abs/2509.18376v2
• Date: Wed, 29 Oct 2025 10:57:22 GMT
• Title: GnnXemplar: Exemplars to Explanations -- Natural Language Rules for Global GNN Interpretability
• Authors: Burouj Armgaan, Eshan Jain, Harsh Pandey, Mahesh Chandran, Sayan Ranu,
• Abstract summary: Graph Neural Networks (GNNs) are widely used for node classification, yet their opaque decision-making limits trust and adoption.<n>We propose GnnXemplar, a novel global explainer inspired from Exemplar Theory from cognitive science.<n>GnnXemplar identifies representative nodes in the GNN embedding space, and explains predictions using natural language rules derived from their neighborhoods.
• Score: 14.490317973333298
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Graph Neural Networks (GNNs) are widely used for node classification, yet their opaque decision-making limits trust and adoption. While local explanations offer insights into individual predictions, global explanation methods, those that characterize an entire class, remain underdeveloped. Existing global explainers rely on motif discovery in small graphs, an approach that breaks down in large, real-world settings where subgraph repetition is rare, node attributes are high-dimensional, and predictions arise from complex structure-attribute interactions. We propose GnnXemplar, a novel global explainer inspired from Exemplar Theory from cognitive science. GnnXemplar identifies representative nodes in the GNN embedding space, exemplars, and explains predictions using natural language rules derived from their neighborhoods. Exemplar selection is framed as a coverage maximization problem over reverse k-nearest neighbors, for which we provide an efficient greedy approximation. To derive interpretable rules, we employ a self-refining prompt strategy using large language models (LLMs). Experiments across diverse benchmarks show that GnnXemplar significantly outperforms existing methods in fidelity, scalability, and human interpretability, as validated by a user study with 60 participants.

Related papers

• From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Context [2.66757978610454]
  LOGIC is a lightweight, post-hoc framework that uses large language models to generate faithful and interpretable explanations for GNN predictions.<n>Our experiments demonstrate that LOGIC achieves a favorable trade-off between fidelity and sparsity, while significantly improving human-centric metrics such as insightfulness.
  arXiv  Detail & Related papers  (2025-08-09T23:22:38Z)
• TreeX: Generating Global Graphical GNN Explanations via Critical Subtree Extraction [38.99239532650183]
  We propose to unbox GNNs by analyzing and extracting critical subtrees incurred by the inner workings of message passing.<n>By aggregating subtrees in an embedding space with an efficient algorithm, we can make intuitive graphical explanations for Message-Passing GNNs on local, class and global levels.
  arXiv  Detail & Related papers  (2025-03-12T04:36:28Z)
• Global Graph Counterfactual Explanation: A Subgraph Mapping Approach [54.42907350881448]
  Graph Neural Networks (GNNs) have been widely deployed in various real-world applications. Counterfactual explanation aims to find minimum perturbations on input graphs that change the GNN predictions. We propose GlobalGCE, a novel global-level graph counterfactual explanation method.
  arXiv  Detail & Related papers  (2024-10-25T21:39:05Z)
• Unveiling Global Interactive Patterns across Graphs: Towards Interpretable Graph Neural Networks [31.29616732552006]
  Graph Neural Networks (GNNs) have emerged as a prominent framework for graph mining. This paper proposes a novel intrinsically interpretable scheme for graph classification. Global Interactive Pattern (GIP) learning introduces learnable global interactive patterns to explicitly interpret decisions.
  arXiv  Detail & Related papers  (2024-07-02T06:31:13Z)
• Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement Learning [49.095065258759895]
  We develop a novel global explanation model RLHEX for molecular property prediction. It aligns the counterfactual explanations with human-defined principles, making the explanations more interpretable and easy for experts to evaluate. The global explanations produced by RLHEX cover 4.12% more input graphs and reduce the distance between the counterfactual explanation set and the input set by 0.47% on average across three molecular datasets.
  arXiv  Detail & Related papers  (2024-06-19T22:16:40Z)
• DEGREE: Decomposition Based Explanation For Graph Neural Networks [55.38873296761104]
  We propose DEGREE to provide a faithful explanation for GNN predictions. By decomposing the information generation and aggregation mechanism of GNNs, DEGREE allows tracking the contributions of specific components of the input graph to the final prediction. We also design a subgraph level interpretation algorithm to reveal complex interactions between graph nodes that are overlooked by previous methods.
  arXiv  Detail & Related papers  (2023-05-22T10:29:52Z)
• Global Explainability of GNNs via Logic Combination of Learned Concepts [11.724402780594257]
  We propose GLGExplainer (Global Logic-based GNN Explainer), the first Global Explainer capable of generating explanations as arbitrary combinations of learned graphical concepts. GLGExplainer provides accurate and human-interpretable global explanations that are perfectly aligned with ground-truth explanations. Extracted formulas are faithful to the model predictions, to the point of providing insights into some occasionally incorrect rules learned by the model.
  arXiv  Detail & Related papers  (2022-10-13T16:30:03Z)
• A Variational Edge Partition Model for Supervised Graph Representation Learning [51.30365677476971]
  This paper introduces a graph generative process to model how the observed edges are generated by aggregating the node interactions over a set of overlapping node communities. We partition each edge into the summation of multiple community-specific weighted edges and use them to define community-specific GNNs. A variational inference framework is proposed to jointly learn a GNN based inference network that partitions the edges into different communities, these community-specific GNNs, and a GNN based predictor that combines community-specific GNNs for the end classification task.
  arXiv  Detail & Related papers  (2022-02-07T14:37:50Z)
• GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks [0.3441021278275805]
  GCExplainer is an unsupervised approach for post-hoc discovery and extraction of global concept-based explanations for graph neural networks (GNNs) We demonstrate the success of our technique on five node classification datasets and two graph classification datasets, showing that we are able to discover and extract high-quality concept representations by putting the human in the loop.
  arXiv  Detail & Related papers  (2021-07-25T20:52:48Z)
• Parameterized Explainer for Graph Neural Network [49.79917262156429]
  We propose PGExplainer, a parameterized explainer for Graph Neural Networks (GNNs) Compared to the existing work, PGExplainer has better generalization ability and can be utilized in an inductive setting easily. Experiments on both synthetic and real-life datasets show highly competitive performance with up to 24.7% relative improvement in AUC on explaining graph classification.
  arXiv  Detail & Related papers  (2020-11-09T17:15:03Z)
• Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking [63.49779304362376]
  Graph neural networks (GNNs) have become a popular approach to integrating structural inductive biases into NLP models. We introduce a post-hoc method for interpreting the predictions of GNNs which identifies unnecessary edges. We show that we can drop a large proportion of edges without deteriorating the performance of the model.
  arXiv  Detail & Related papers  (2020-10-01T17:51:19Z)

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.