Graph Neural Networks (GNNs) have received increasing attention due to their ability to learn from graphstructured data. To open the blackbox of these deep learning models, posthoc instancelevel explanation methods have been proposed to understand GNN predictions. These methods seek to discover substructures that explain the prediction behavior of a trained GNN. In this paper, we show analytically that for a large class of explanation tasks, conventional approaches, which are based on the principle of graph information bottleneck (GIB), admit trivial solutions that do not align with the notion of explainability. Instead, we argue that a modified GIB principle may be used to avoid the aforementioned trivial solutions. We further introduce a novel factorized explanation model with theoretical performance guarantees. The modified GIB is used to analyze the structural properties of the proposed factorized explainer. We conduct extensive experiments on both synthetic and realworld datasets to validate the effectiveness of our proposed factorized explainer.
This content will become publicly available on July 1, 2025
With the increasing popularity of Graph Neural Networks (GNNs) for predictive tasks on graph structured data, research on their explainability is becoming more critical and achieving significant progress. Although many methods are proposed to explain the predictions of GNNs, their focus is mainly on “how to generate explanations.” However, other important research questions like “whether the GNN explanations are inaccurate,” “what if the explanations are inaccurate,” and “how to adjust the model to generate more accurate explanations” have gained little attention. Our previous GNN Explanation Supervision (GNES) framework demonstrated effectiveness on improving the reasonability of the local explanation while still keep or even improve the backbone GNNs model performance. In many applications instead of per sample explanations, we need to find global explanations which are reasonable and faithful to the domain data. Simply learning to explain GNNs locally is not an optimal solution to a global understanding of the model. To improve the explainability power of the GNES framework, we propose the Global GNN Explanation Supervision (GGNES) technique which uses a basic trained GNN and a global extension of the loss function used in the GNES framework. This GNN creates local explanations which are fed to a Global Logicbased GNN Explainer, an existing technique that can learn the global Explanation in terms of a logic formula. These two frameworks are then trained iteratively to generate reasonable global explanations. Extensive experiments demonstrate the effectiveness of the proposed model on improving the global explanations while keeping the performance similar or even increase the model prediction power.
more » « less NSFPAR ID:
 10520957
 Publisher / Repository:
 ACL
 Date Published:
 Journal Name:
 Frontiers in Big Data
 Volume:
 7
 ISSN:
 2624909X
 Format(s):
 Medium: X
 Sponsoring Org:
 National Science Foundation
More Like this


Despite recent progress in Graph Neural Networks (GNNs), explaining predictions made by GNNs remains a challenging and nascent problem. The leading method mainly considers the local explanations, i.e., important subgraph structure and node features, to interpret why a GNN model makes the prediction for a single instance, e.g. a node or a graph. As a result, the explanation generated is painstakingly customized at the instance level. The unique explanation interpreting each instance independently is not sufficient to provide a global understanding of the learned GNN model, leading to the lack of generalizability and hindering it from being used in the inductive setting. Besides, training the explanation model explaining for each instance is timeconsuming for largescale reallife datasets. In this study, we address these key challenges and propose PGExplainer, a parameterized explainer for GNNs. PGExplainer adopts a deep neural network to parameterize the generation process of explanations, which renders PGExplainer a natural approach to multiinstance explanations. Compared to the existing work, PGExplainer has better generalization ability and can be utilized in an inductive setting without training the model for new instances. Thus, PGExplainer is much more efficient than the leading method with significant speedup. In addition, the explanation networks can also be utilized as a regularizer to improve the generalization power of existing GNNs when jointly trained with downstream tasks. Experiments on both synthetic and reallife datasets show highly competitive performance with up to 24.7% relative improvement in AUC on explaining graph classification over the leading baseline.more » « less

Graph Neural Networks (GNNs) are neural models that leverage the dependency structure in graphical data via message passing among the graph nodes. GNNs have emerged as pivotal architectures in analyzing graphstructured data, and their expansive application in sensitive domains requires a comprehensive understanding of their decisionmaking processes — necessitating a framework for GNN explainability. An explanation function for GNNs takes a pretrained GNN along with a graph as input, to produce a ‘sufficient statistic’ subgraph with respect to the graph label. A main challenge in studying GNN explainability is to provide fidelity measures that evaluate the performance of these explanation functions. This paper studies this foundational challenge, spotlighting the inherent limitations of prevailing fidelity metrics, including Fid+, Fid−, and Fid∆. Specifically, a formal, informationtheoretic definition of explainability is introduced and it is shown that existing metrics often fail to align with this definition across various statistical scenarios. The reason is due to potential distribution shifts when subgraphs are removed in computing these fidelity measures. Subsequently, a robust class of fidelity measures are introduced, and it is shown analytically that they are resilient to distribution shift issues and are applicable in a wide range of scenarios. Extensive empirical analysis on both synthetic and real datasets are provided to illustrate that the proposed metrics are more coherent with gold standard metrics. The source code is available at https://trustai4slab.github.io/fidelity.more » « less

Graph Neural Networks (GNNs) have shown satisfying performance in various graph analytical problems. Hence, they have become the de facto solution in a variety of decisionmaking scenarios. However, GNNs could yield biased results against certain demographic subgroups. Some recent works have empirically shown that the biased structure of the input network is a significant source of bias for GNNs. Nevertheless, no studies have systematically scrutinized which part of the input network structure leads to biased predictions for any given node. The low transparency on how the structure of the input network influences the bias in GNN outcome largely limits the safe adoption of GNNs in various decisioncritical scenarios. In this paper, we study a novel research problem of structural explanation of bias in GNNs. Specifically, we propose a novel posthoc explanation framework to identify two edge sets that can maximally account for the exhibited bias and maximally contribute to the fairness level of the GNN prediction for any given node, respectively. Such explanations not only provide a comprehensive understanding of bias/fairness of GNN predictions but also have practical significance in building an effective yet fair GNN model. Extensive experiments on realworld datasets validate the effectiveness of the proposed framework towards delivering effective structural explanations for the bias of GNNs. Opensource code can be found at https://github.com/yushundong/REFEREE.more » « less

In recent years, analyzing the explanation for the prediction of Graph Neural Networks (GNNs) has attracted increasing attention. Despite this progress, most existing methods do not adequately consider the inherent uncertainties stemming from the randomness of model parameters and graph data, which may lead to overconfidence and misguiding explanations. However, it is challenging for most of GNN explanation methods to quantify these uncertainties since they obtain the prediction explanation in a
posthoc and modelagnostic manner without considering the randomness ofgraph data andmodel parameters . To address the above problems, this paper proposes a novel uncertainty quantification framework for GNN explanations. For mitigating the randomness of graph data in the explanation, our framework accounts for two distinct data uncertainties, allowing for a direct assessment of the uncertainty in GNN explanations. For mitigating the randomness of learned model parameters, our method learns the parameter distribution directly from the data, obviating the need for assumptions about specific distributions. Moreover, the explanation uncertainty within model parameters is also quantified based on the learned parameter distributions. This holistic approach can integrate with anyposthoc GNN explanation methods. Empirical results from our study show that our proposed method sets a new standard for GNN explanation performance across diverse realworld graph benchmarks.