Graph Neural Networks (GNNs) are a powerful tool for machine learning on graphs.

As a result, the explanation generated is painstakingly customized foreachinstance.

If a lattice L is distributive, then L is also modular . By assuming x y, we have x y = y . Hence, from the distributive property we get: x (y z) ( x y) (x z) y ( x z) 14 Definition A.7. Congruence Lattice Reflexivity: For every element a in A, a is related to itself, denoted as a a; Symmetry: For any elements a and b in A, if a b, then b a; Transitivity: For any elements a, b, and c in A, if a b and b c, then a c . An algebra with no other congruences is called simple . A type F is defined as a set of operation symbols along with their respective arities.

In this section, we analyze the vanilla gradient-based explainers and GNNExplainer [24] under the explanation model framework. The proof that this explanation method falls into the class ofadditive feature attribution methods is quite straight-forward. TheconditionG S indicates thattherealization of G must be consistent with the realization of subgraphS. Thus, GNNExplainer would fail to explain predictions of thosemodels. In Figure 1, we provide an example illustrating the impact of theno-child constraint (3) onto the PGMexplanation. However, the constraint changes the edges in the Bayesian network.

Graph Neural Networks (GNNs) are a powerful tool for machine learning on graphs.GNNs combine node feature information with the graph structure by recursively passing neural messages along edges of the input graph. However, incorporating both graph structure and feature information leads to complex models, and explaining predictions made by GNNs remains unsolved. Here we propose GNNExplainer, the first general, model-agnostic approach for providing interpretable explanations for predictions of any GNN-based model on any graph-based machine learning task. Given an instance, GNNExplainer identifies a compact subgraph structure and a small subset of node features that have a crucial role in GNN's prediction. Further, GNNExplainer can generate consistent and concise explanations for an entire class of instances. We formulate GNNExplainer as an optimization task that maximizes the mutual information between a GNN's prediction and distribution of possible subgraph structures. Experiments on synthetic and real-world graphs show that our approach can identify important graph structures as well as node features, and outperforms baselines by 17.1% on average. GNNExplainer provides a variety of benefits, from the ability to visualize semantically relevant structures to interpretability, to giving insights into errors of faulty GNNs.

If a lattice L is distributive, then L is also modular . By assuming x y, we have x y = y . Hence, from the distributive property we get: x (y z) ( x y) (x z) y ( x z) 14 Definition A.7. Congruence Lattice Reflexivity: For every element a in A, a is related to itself, denoted as a a; Symmetry: For any elements a and b in A, if a b, then b a; Transitivity: For any elements a, b, and c in A, if a b and b c, then a c . An algebra with no other congruences is called simple . A type F is defined as a set of operation symbols along with their respective arities.

The risk of financial fraud is increasing as digital payments are used more and more frequently. Although the use of artificial intelligence systems for fraud detection is widespread, society and regulators have raised the standards for these systems' transparency for reliability verification purposes. To increase their effectiveness in conducting fraud investigations, fraud analysts also profit from having concise and understandable explanations. To solve these challenges, the paper will concentrate on developing an explainable fraud detector.

Control Flow Graphs (CFGs) are critical for analyzing program execution and characterizing malware behavior. With the growing adoption of Graph Neural Networks (GNNs), CFG-based representations have proven highly effective for malware detection. This study proposes a novel framework that dynamically constructs CFGs and embeds node features using a hybrid approach combining rule-based encoding and autoencoder-based embedding. A GNN-based classifier is then constructed to detect malicious behavior from the resulting graph representations. To improve model interpretability, we apply state-of-the-art explainability techniques, including GNNExplainer, PGExplainer, and CaptumExplainer, the latter is utilized three attribution methods: Integrated Gradients, Guided Backpropagation, and Saliency. In addition, we introduce a novel aggregation method, called RankFusion, that integrates the outputs of the top-performing explainers to enhance the explanation quality. We also evaluate explanations using two subgraph extraction strategies, including the proposed Greedy Edge-wise Composition (GEC) method for improved structural coherence. A comprehensive evaluation using accuracy, fidelity, and consistency metrics demonstrates the effectiveness of the proposed framework in terms of accurate identification of malware samples and generating reliable and interpretable explanations.