Interpretability of Graph Neural Networks

GNNBook@2023: Interpretability in Graph Neural Networks

In this chapter, we offer a comprehensive survey to summarize these approaches. Specifically, in the first section, we review the fundamental concepts of ...

How Interpretable Are Interpretable Graph Neural Networks? - arXiv

In this work, we present a theoretical framework that formulates interpretable subgraph learning with the multilinear extension of the subgraph distribution.

Interpretability in Graph Neural Networks

In graph analysis, motivated by the effectiveness of deep learning, graph neural networks (GNNs) are becoming increasingly popular in modeling graph data.

GNNExplainer: Generating Explanations for Graph Neural Networks

Figure 1: GNNEXPLAINER provides interpretable explanations for predictions made by any GNN model on any graph-based machine learning task. Shown is a ...

Global Concept-Based Interpretability for Graph Neural Networks via ...

Title:Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysis ... Abstract:Graph neural networks (GNNs) are highly ...

Pre-training Interpretable Graph Neural Networks - NIPS papers

Intrinsic interpretable graph neural networks aim to provide transparent predictions by identifying the influential fraction of the input graph that guides ...

Graph neural networks for an accurate and interpretable prediction ...

We develop a graph neural network (GNN) model for obtaining an embedding of polycrystalline microstructure which incorporates not only the physical features of ...

Interpretability in Graph Neural Networks - SpringerLink

Interpretable machine learning, or explainable artificial intelligence, is experiencing rapid developments to tackle the opacity issue of ...

KerGNNs: Interpretable Graph Neural Networks with Graph Kernels

Inspired by convolution filters in convolutional neural networks (CNNs), KerGNNs adopt trainable hidden graphs as graph filters which are combined with ...

Interpretability Methods for Graph Neural Networks - IEEE Xplore

The emerging graph neural network models (GNNs) have demonstrated great potential and success for downstream graph machine learning tasks, such as graph and ...

A graph-based interpretability method for deep neural networks

In this paper, we propose a graph-based interpretability method for deep neural networks (GIMDNN). The running parameters of DNNs are modeled as a graph.

Explaining Graph Neural Networks Using Interpretable Local ...

Graph Neural Network Explainability focuses on developing methods to interpret GNNs, allowing users to trust and com- prehend their outputs. Various techniques ...

A Demonstration of Interpretability Methods for Graph Neural Networks

This paper demonstrates gInterpreter with an interactive performance profiling of 15 recent GNN inter-pretability methods, aiming to explain the complex deep ...

flyingdoog/awesome-graph-explainability-papers - GitHub

[ICML 24] How Interpretable Are Interpretable Graph Neural Networks? ... [AAAI 23] Global Concept-Based Interpretability for Graph Neural Networks via Neuron ...

Towards interpretable graph neural networks for transport prediction ...

In this paper, we use Neural Relational Inference to learn the optimal graph for the model. Our approach has several advantages.

Interpretable and Convergent Graph Neural Network Layers at Scale

Among the many variants of graph neural network (GNN) architectures capable of modeling data with cross-instance relations, an important ...

Global concept-based interpretability for graph neural networks via ...

Abstract. Graph neural networks (GNNs) are highly effective on a variety of graph-related tasks; however, they lack interpretability and transparency. Current ...

Interpretability in Graph Neural Networks - ResearchGate

... Interpretability in deep neural networks can be defined as the degree to which an observer understands the decision of a model (61) . This can be broken ...

Efficient and interpretable graph network representation for angle ...

Graph neural networks are attractive for learning properties of atomic structures thanks to their intuitive graph encoding of atoms and ...

Interpretability Methods for Graph Neural Networks

Abstract—The emerging graph neural network models (GNNs) have demonstrated great potential and success for downstream graph machine learning tasks, ...