# Beyond Soft Masks: Hard-Perturbation Mixup Explainer for Robust GNN Explainability

arXiv: https://arxiv.org/abs/2606.05756 · HTML: https://mlsanity.com/paper/2606.05756/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 48 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Builds on (most cited first, 27 of 27)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Link Prediction Based on Graph Neural Networks](https://mlsanity.com/paper/1802.09691/) (2018)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [Graph U-Nets](https://mlsanity.com/paper/1905.05178/) (2019)
- [Parameterized Explainer for Graph Neural Network](https://mlsanity.com/paper/2011.04573/) (2020)
- [Self-Attention Graph Pooling](https://mlsanity.com/paper/1904.08082/) (2019)
- [GemNet: Universal Directional Graph Neural Networks for Molecules](https://mlsanity.com/paper/2106.08903/) (2021)
- [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)
- [Can Graph Neural Networks Count Substructures?](https://mlsanity.com/paper/2002.04025/) (2020)
- [XGNN: Towards Model-Level Explanations of Graph Neural Networks](https://mlsanity.com/paper/2006.02587/) (2020)
- [Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism](https://mlsanity.com/paper/2201.12987/) (2022)
- [Graph Information Bottleneck](https://mlsanity.com/paper/2010.12811/) (2020)
- [Learning the Graphical Structure of Electronic Health Records with Graph Convolutional Transformer](https://mlsanity.com/paper/1906.04716/) (2019)
- [GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Games](https://mlsanity.com/paper/2201.12380/) (2022)
- [Contrastive Graph Neural Network Explanation](https://mlsanity.com/paper/2010.13663/) (2020)
- [MixupExplainer: Generalizing Explanations for Graph Neural Networks with Data Augmentation](https://mlsanity.com/paper/2307.07832/) (2023)
- [Modeling Network-level Traffic Flow Transitions on Sparse Data](https://mlsanity.com/paper/2208.06646/) (2022)
- [Explaining Graph Neural Networks via Structure-aware Interaction Index](https://mlsanity.com/paper/2405.14352/) (2024)
- [GInX-Eval: Towards In-Distribution Evaluation of Graph Neural Network Explanations](https://mlsanity.com/paper/2309.16223/) (2023)
- [Rethinking Explaining Graph Neural Networks via Non-parametric Subgraph Matching](https://mlsanity.com/paper/2301.02780/) (2023)
- [MAGE: Model-Level Graph Neural Networks Explanations via Motif-based Graph Generation](https://mlsanity.com/paper/2405.12519/) (2024)
- [RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanation](https://mlsanity.com/paper/2505.02247/) (2025)

## Abstract (arXiv)

Graph Neural Networks (GNNs) have demonstrated remarkable performance across a range of applications involving graph-structured data, particularly in high-stakes domains. However, the opaque nature of their decision-making processes limits their trustworthiness and broader adoption. Existing post-hoc explanation methods aim to improve explainability by identifying subgraphs that influence GNN predictions and adopt mixup strategies to alleviate the out-of-distribution (OOD) issue caused by using subgraphs for prediction. Yet, these approaches typically rely on soft masks, which are inherently unable to fully eliminate label-irrelevant information, allowing redundant structures to leak into the mixup process and hindering the resolution of the OOD problem, thereby degrading explanation fidelity. In this work, we propose HPME, a Hard-Perturbation Mixup Explanation framework grounded in a generalized Graph Information Bottleneck, which leverages graph pooling to extract discrete explanatory subgraphs and to yield an information-capacity bound to thoroughly compress label-irrelevant components. Furthermore, we introduce a novel mixup strategy built upon structure-level replacement, generating in-distribution explanations to effectively mitigate the distribution shift. Extensive experiments on diverse tasks demonstrate that HPME achieves state-of-the-art performance in generating robust and interpretable explanations across both synthetic and real-world datasets.