Towards Faithful Class-level Self-explainability in Graph Neural Networks by Subgraph Dependencies

• URL: http://arxiv.org/abs/2508.11513v1
• Date: Fri, 15 Aug 2025 14:44:11 GMT
• Title: Towards Faithful Class-level Self-explainability in Graph Neural Networks by Subgraph Dependencies
• Authors: Fanzhen Liu, Xiaoxiao Ma, Jian Yang, Alsharif Abuadbba, Kristen Moore, Surya Nepal, Cecile Paris, Quan Z. Sheng, Jia Wu,
• Abstract summary: Recent work has introduced graph neural networks (GNNs) that generate explanations as part of training.<n>Some models, such as ProGNN and PGIB, offer a pathway toward class-specific prototypes.<n>We introduce a novel self-explainable GNN that learns and generalizes for class-level explanations.
• Score: 38.551080206570965
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Enhancing the interpretability of graph neural networks (GNNs) is crucial to ensure their safe and fair deployment. Recent work has introduced self-explainable GNNs that generate explanations as part of training, improving both faithfulness and efficiency. Some of these models, such as ProtGNN and PGIB, learn class-specific prototypes, offering a potential pathway toward class-level explanations. However, their evaluations focus solely on instance-level explanations, leaving open the question of whether these prototypes meaningfully generalize across instances of the same class. In this paper, we introduce GraphOracle, a novel self-explainable GNN framework designed to generate and evaluate class-level explanations for GNNs. Our model jointly learns a GNN classifier and a set of structured, sparse subgraphs that are discriminative for each class. We propose a novel integrated training that captures graph$\unicode{x2013}$subgraph$\unicode{x2013}$prediction dependencies efficiently and faithfully, validated through a masking-based evaluation strategy. This strategy enables us to retroactively assess whether prior methods like ProtGNN and PGIB deliver effective class-level explanations. Our results show that they do not. In contrast, GraphOracle achieves superior fidelity, explainability, and scalability across a range of graph classification tasks. We further demonstrate that GraphOracle avoids the computational bottlenecks of previous methods$\unicode{x2014}$like Monte Carlo Tree Search$\unicode{x2014}$by using entropy-regularized subgraph selection and lightweight random walk extraction, enabling faster and more scalable training. These findings position GraphOracle as a practical and principled solution for faithful class-level self-explainability in GNNs.

Related papers

• 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)
• GNNAnatomy: Rethinking Model-Level Explanations for Graph Neural Networks [20.05098366613674]
  Graph Neural Networks (GNNs) achieve outstanding performance across graph-based tasks but remain difficult to interpret.<n>This paper introduces GNNAnatomy, a distillation-based method designed to generate explanations while avoiding pitfalls.<n>To account for structural diversity within a class, GNNAnatomy generates explanations at the required granularity through an interface that supports human-AI teaming.
  arXiv  Detail & Related papers  (2024-06-06T23:09:54Z)
• View-based Explanations for Graph Neural Networks [27.19300566616961]
  We propose GVEX, a novel paradigm that generates Graph Views for EXplanation. We show that this strategy provides an approximation ratio of 1/2. Our second algorithm performs a single-pass to an input node stream in batches to incrementally maintain explanation views.
  arXiv  Detail & Related papers  (2024-01-04T06:20:24Z)
• How Graph Neural Networks Learn: Lessons from Training Dynamics [80.41778059014393]
  We study the training dynamics in function space of graph neural networks (GNNs) We find that the gradient descent optimization of GNNs implicitly leverages the graph structure to update the learned function. This finding offers new interpretable insights into when and why the learned GNN functions generalize.
  arXiv  Detail & Related papers  (2023-10-08T10:19:56Z)
• PAGE: Prototype-Based Model-Level Explanations for Graph Neural Networks [12.16789930553124]
  Prototype-bAsed GNN-Explainer (Page) is a novel model-level explanation method for graph classification. Page discovers a common subgraph pattern by iteratively searching for high matching nodes. Using six graph classification datasets, we demonstrate that PAGE qualitatively and quantitatively outperforms the state-of-the-art model-level explanation method.
  arXiv  Detail & Related papers  (2022-10-31T09:10:06Z)
• Neural Graph Matching for Pre-training Graph Neural Networks [72.32801428070749]
  Graph neural networks (GNNs) have been shown powerful capacity at modeling structural data. We present a novel Graph Matching based GNN Pre-Training framework, called GMPT. The proposed method can be applied to fully self-supervised pre-training and coarse-grained supervised pre-training.
  arXiv  Detail & Related papers  (2022-03-03T09:53:53Z)
• A Meta-Learning Approach for Training Explainable Graph Neural Networks [10.11960004698409]
  We propose a meta-learning framework for improving the level of explainability of a GNN directly at training time. Our framework jointly trains a model to solve the original task, e.g., node classification, and to provide easily processable outputs for downstream algorithms. Our model-agnostic approach can improve the explanations produced for different GNN architectures and use any instance-based explainer to drive this process.
  arXiv  Detail & Related papers  (2021-09-20T11:09:10Z)
• Towards Self-Explainable Graph Neural Network [24.18369781999988]
  Graph Neural Networks (GNNs) generalize the deep neural networks to graph-structured data. GNNs lack explainability, which limits their adoption in scenarios that demand the transparency of models. We propose a new framework which can find $K$-nearest labeled nodes for each unlabeled node to give explainable node classification.
  arXiv  Detail & Related papers  (2021-08-26T22:45:11Z)
• 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)
• Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning [63.97983530843762]
  Graph Neural Networks (GNNs) have achieved great success in graph representation learning. GNNs generate identical representations for graph substructures that may in fact be very different. More powerful GNNs, proposed recently by mimicking higher-order tests, are inefficient as they cannot sparsity of underlying graph structure. We propose Distance Depiction (DE) as a new class of graph representation learning.
  arXiv  Detail & Related papers  (2020-08-31T23:15:40Z)
• XGNN: Towards Model-Level Explanations of Graph Neural Networks [113.51160387804484]
  Graphs neural networks (GNNs) learn node features by aggregating and combining neighbor information. GNNs are mostly treated as black-boxes and lack human intelligible explanations. We propose a novel approach, known as XGNN, to interpret GNNs at the model-level.
  arXiv  Detail & Related papers  (2020-06-03T23:52:43Z)

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.