# SliceGX: Layer-wise GNN Explanation with Model-slicing

arXiv: https://arxiv.org/abs/2506.17977 · HTML: https://mlsanity.com/paper/2506.17977/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 62 references that are in the map.
- First posted on arXiv 22 Jun 2025.

## Builds on (most cited first, 29 of 29)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Representation Learning on Graphs with Jumping Knowledge Networks](https://mlsanity.com/paper/1806.03536/) (2018)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [GraphSAINT: Graph Sampling Based Inductive Learning Method](https://mlsanity.com/paper/1907.04931/) (2019)
- [Parameterized Explainer for Graph Neural Network](https://mlsanity.com/paper/2011.04573/) (2020)
- [Explainability in Graph Neural Networks: A Taxonomic Survey](https://mlsanity.com/paper/2012.15445/) (2020)
- [On Explainability of Graph Neural Networks via Subgraph Explorations](https://mlsanity.com/paper/2102.05152/) (2021)
- [Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters](https://mlsanity.com/paper/2008.08692/) (2020)
- [Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking](https://mlsanity.com/paper/2010.00577/) (2020)
- [Debugging Tests for Model Explanations](https://mlsanity.com/paper/2011.05429/) (2020)
- [Higher-Order Explanations of Graph Neural Networks via Relevant Walks](https://mlsanity.com/paper/2006.03589/) (2020)
- [Scalable Graph Neural Networks via Bidirectional Propagation](https://mlsanity.com/paper/2010.15421/) (2020)
- [Robust Counterfactual Explanations on Graph Neural Networks](https://mlsanity.com/paper/2107.04086/) (2021)
- [GraphSVX: Shapley Value Explanations for Graph Neural Networks](https://mlsanity.com/paper/2104.10482/) (2021)
- [A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challenges](https://mlsanity.com/paper/2403.04468/) (2024)
- [RelEx: A Model-Agnostic Relational Model Explainer](https://mlsanity.com/paper/2006.00305/) (2020)
- [KerGNNs: Interpretable Graph Neural Networks with Graph Kernels](https://mlsanity.com/paper/2201.00491/) (2022)
- [Can I Trust the Explainer? Verifying Post-hoc Explanatory Methods](https://mlsanity.com/paper/1910.02065/) (2019)
- [Grain: Improving Data Efficiency of Graph Neural Networks via Diversified Influence Maximization](https://mlsanity.com/paper/2108.00219/) (2021)
- [FlowX: Towards Explainable Graph Neural Networks via Message Flows](https://mlsanity.com/paper/2206.12987/) (2022)
- [Dynamic Slicing for Deep Neural Networks](https://mlsanity.com/paper/2009.13747/) (2020)
- [Model Slicing for Supporting Complex Analytics with Elastic Inference Cost and Resource Constraints](https://mlsanity.com/paper/1904.01831/) (2019)
- [A Survey of RDF Stores & SPARQL Engines for Querying Knowledge Graphs](https://mlsanity.com/paper/2102.13027/) (2021)
- [Powering In-Database Dynamic Model Slicing for Structured Data Analytics](https://mlsanity.com/paper/2405.00568/) (2024)

## Built on by (most cited first, 1 of 1)

- [A Tight Expressivity Hierarchy for GNN-Based Entity Resolution in Master Data Management](https://mlsanity.com/paper/2603.27154/) (2026)

## Abstract (arXiv)

Ensuring the trustworthiness of graph neural networks (GNNs), which are often treated as black-box models, requires effective explanation techniques. Existing GNN explanations typically apply input perturbations to identify subgraphs that are responsible for the occurrence of the final output of GNNs. However, such approaches lack finer-grained, layer-wise analysis of how intermediate representations contribute to the final result, capabilities that are crucial for model diagnosis and architecture optimization. This paper introduces SliceGX, a novel GNN explanation approach that generates explanations at specific GNN layers in a progressive manner. Given a GNN model M, a set of selected intermediate layers, and a target layer, SliceGX slices M into layer blocks("model slice") and discovers high-quality explanatory subgraphs within each block that elucidate how the model output arises at the target layer. Although finding such layer-wise explanations is computationally challenging, we develop efficient algorithms and optimization techniques that incrementally construct and maintain these subgraphs with provable approximation guarantees. Extensive experiments on synthetic and real-world benchmarks demonstrate the effectiveness and efficiency of SliceGX, and illustrate its practical utility in supporting model debugging.