Explainable Graph Neural Networks Under Fire
- URL: http://arxiv.org/abs/2406.06417v1
- Date: Mon, 10 Jun 2024 16:09:16 GMT
- Title: Explainable Graph Neural Networks Under Fire
- Authors: Zhong Li, Simon Geisler, Yuhang Wang, Stephan Günnemann, Matthijs van Leeuwen,
- Abstract summary: Graph neural networks (GNNs) usually lack interpretability due to their complex computational behavior and the abstract nature of graphs.
Most GNN explanation methods work in a post-hoc manner and provide explanations in the form of a small subset of important edges and/or nodes.
In this paper we demonstrate that these explanations can unfortunately not be trusted, as common GNN explanation methods turn out to be highly susceptible to adversarial perturbations.
- Score: 69.15708723429307
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Predictions made by graph neural networks (GNNs) usually lack interpretability due to their complex computational behavior and the abstract nature of graphs. In an attempt to tackle this, many GNN explanation methods have emerged. Their goal is to explain a model's predictions and thereby obtain trust when GNN models are deployed in decision critical applications. Most GNN explanation methods work in a post-hoc manner and provide explanations in the form of a small subset of important edges and/or nodes. In this paper we demonstrate that these explanations can unfortunately not be trusted, as common GNN explanation methods turn out to be highly susceptible to adversarial perturbations. That is, even small perturbations of the original graph structure that preserve the model's predictions may yield drastically different explanations. This calls into question the trustworthiness and practical utility of post-hoc explanation methods for GNNs. To be able to attack GNN explanation models, we devise a novel attack method dubbed \textit{GXAttack}, the first \textit{optimization-based} adversarial attack method for post-hoc GNN explanations under such settings. Due to the devastating effectiveness of our attack, we call for an adversarial evaluation of future GNN explainers to demonstrate their robustness.
Related papers
- Graph Neural Network Explanations are Fragile [39.9987140075811]
We take the first step to study GNN explainers under adversarial attack.
We find that an adversary slightly perturbing graph structure can ensure GNN model makes correct predictions, but the GNN explainer yields a drastically different explanation on the perturbed graph.
arXiv Detail & Related papers (2024-06-05T12:23:02Z) - Incorporating Retrieval-based Causal Learning with Information
Bottlenecks for Interpretable Graph Neural Networks [12.892400744247565]
We develop a novel interpretable causal GNN framework that incorporates retrieval-based causal learning with Graph Information Bottleneck (GIB) theory.
We achieve 32.71% higher precision on real-world explanation scenarios with diverse explanation types.
arXiv Detail & Related papers (2024-02-07T09:57:39Z) - On Consistency in Graph Neural Network Interpretation [34.25952902469481]
Instance-level GNN explanation aims to discover critical input elements, like nodes or edges, that the target GNN relies upon for making predictions.
Various algorithms are proposed, but most of them formalize this task by searching the minimal subgraph.
We propose a simple yet effective countermeasure by aligning embeddings.
arXiv Detail & Related papers (2022-05-27T02:58:07Z) - Reinforced Causal Explainer for Graph Neural Networks [112.57265240212001]
Explainability is crucial for probing graph neural networks (GNNs)
We propose a reinforcement learning agent, Reinforced Causal Explainer (RC-Explainer)
RC-Explainer generates faithful and concise explanations, and has a better power to unseen graphs.
arXiv Detail & Related papers (2022-04-23T09:13:25Z) - Task-Agnostic Graph Explanations [50.17442349253348]
Graph Neural Networks (GNNs) have emerged as powerful tools to encode graph structured data.
Existing learning-based GNN explanation approaches are task-specific in training.
We propose a Task-Agnostic GNN Explainer (TAGE) trained under self-supervision with no knowledge of downstream tasks.
arXiv Detail & Related papers (2022-02-16T21:11:47Z) - 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) - Jointly Attacking Graph Neural Network and its Explanations [50.231829335996814]
Graph Neural Networks (GNNs) have boosted the performance for many graph-related tasks.
Recent studies have shown that GNNs are highly vulnerable to adversarial attacks, where adversaries can mislead the GNNs' prediction by modifying graphs.
We propose a novel attack framework (GEAttack) which can attack both a GNN model and its explanations by simultaneously exploiting their vulnerabilities.
arXiv Detail & Related papers (2021-08-07T07:44:33Z) - 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) - 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.