Declarative Explanations for Graph Neural Networks: A Demonstration

Cibo Yu; Haitong Tang; Yinghui Wu; Arijit Khan; Tingting Zhu; Tingyang Chen; Xiangyu Ke

cs.LGOct 19, 2026

Declarative Explanations for Graph Neural Networks: A Demonstration

Authors: Cibo Yu, Haitong Tang, Yinghui Wu, Arijit Khan, Tingting Zhu, Tingyang Chen, Xiangyu Ke

Organizations: Zhejiang University, Hangzhou, China · Case Western Reserve University, Cleveland, USA · Bowling Green State University, Bowling Green, USA

Abstract

Graph Neural Networks (GNNs) have proven effective for graph analytical tasks, yet their "black-box" nature complicates the understanding of their layer-wise behavior and hinders their application to large graphs. We demonstrate SliceGXQ, an end-to-end declarative and interactive system for querying and exploring layer-wise explanations for GNNs over large-scale graphs. In particular, SliceGXQ provides (1) an interactive graphical user interface for dataset, model, and explanation configuration; (2) a lightweight SPARQL-like parser that allows users to specify target nodes, layers, explanation modes, and constraints; and (3) an integrated execution and visualization workflow that invokes SliceGX as its underlying explanation engine. We demonstrate how users can diagnose a misclassified node, identify problematic layers and influential messages, and perform targeted model debugging, together with large-scale graph interpretation and fraud-detection analysis. Our demonstration video and source code are available at https://github.com/jinzhaoqet/SliceGXQ.

Figures & tables

Fig. 1: $\mathsf{SliceGXQ}$ workflow. Users select a graph and a $\mathsf{GNN}$ model, submit an explanation request, and inspect the layer-wise results returned.

Fig. 4: End-to-end workflow of $\mathsf{SliceGXQ}$ . The left panels show dataset and model selection and the two query input modes; the right panels show layer-wise explanation results and user-initiated model debugging. In the output panel, red and yellow nodes indicate predictions of “Fraud” and “Benign”, respectively; blue-bordered and red-bordered nodes are explanatory and connector nodes, respectively.

Fig. 5: Explanation-generation time and fidelity of $\mathsf{SliceGXQ}$ across GNN layers on an NVIDIA GeForce RTX 3080 GPU. GNNExplainer and SubgraphX appear only at Layer 3 as final-output explainers.

GNN Explainability

Graph neural network explainability studies how to identify and communicate the features, nodes, edges, and subgraphs behind graph-model predictions.

See all 80 papers

CIExplainer++: Generating Causal and Interpretable Explanations for Graph Neural Networks
Jun 17, 2026Francisco Caldas, Sahil Satish Kumar, Ruben Belo +1Natural Language Explanation Generation Causal Interpretability
NOVA LINCS, NOVA School of Science and Technology, Lisbon, Portugal
GRAFT: Auditing Graph Neural Networks via Global Feature Attribution
May 5, 2026Rishi Raj Sahoo, Subhankar MishraFeature Attribution Graph Neural Networks
National Institute of Science Education and Research (NISER), Bhubaneswar, India · Homi Bhabha National Institute, Mumbai, India
Beyond Trained Models: Compiling GNNs for a Sound Explainer Benchmark
Oct 2, 2026Steve Azzolin, Francesco Paolo Nerini, Stefano Teso +4GNN Explainability Explainability Evaluation
University of Trento Trento, Italy

Jun 17, 2026J/K move · Enter open · S save

CIExplainer++: Generating Causal and Interpretable Explanations for Graph Neural Networks

Francisco Caldas, Sahil Satish Kumar, Ruben Belo, Cláudia Soares

NOVA LINCS, NOVA School of Science and Technology, Lisbon, Portugal

Natural Language Explanation Generation Causal Interpretability GNN Explainability

Open paper AskPDF arXiv

Explainable Artificial Intelligence aims to make black-box models more trustworthy by presenting, in a human-understandable manner, the elements that lead to the model's output. This involves both (i) identifying components and connections with genuine causal influence on outputs and (ii) translating such structures into an interpretable representation. For the former, we introduce CIExplainer, a novel perturbation-based method grounded in causal inference for explaining Graph Neural Networks (GNNs). CIExplainer identifies the subgraph with the highest causal effects on GNN predictions using the Potential Outcome Framework. We evaluate and compare CIExplainer on various GNN architectures (GCN, GraphSAGE, GAT, GIN) and datasets. To bridge subgraph explanations with human interpretability, we further propose G2TeXplainer, a method that transforms causal subgraphs into natural language explanations that capture both feature-level and relational information.

Abstract

GNN Explainability

Explore similar work

CIExplainer++: Generating Causal and Interpretable Explanations for Graph Neural Networks

GRAFT: Auditing Graph Neural Networks via Global Feature Attribution

Beyond Trained Models: Compiling GNNs for a Sound Explainer Benchmark