Interpretability of Graph Neural Networks

Interpretable neural networks: principles and applications - Frontiers

The interpretability of neural networks has now become a research hotspot in the field of deep learning. It covers a wide range of topics in speech and text ...

Discovering Invariant Rationales for Graph Neural Networks

Intrinsic interpretability of graph neural networks (GNNs) is to find a small subset of the input graph's features -- rationale -- which guides the model ...

Graph Neural Networks (GNNs) - Comprehensive Guide - viso.ai

Neural Networks (NNs): While NNs can learn complex patterns in data, interpreting these patterns and how they relate to the structure of the ...

How to interpret the global max pooling operation in graph neural ...

0 I'm trying to use pytorch geometric for building graph convolutional networks. And I'm trying to interpret the result of the max pooling ...

Predicting molecular properties based on the interpretable graph ...

Particularly, graph neural networks show superior performance in molecular property prediction due to the fact that the molecules could be ...

Evaluating Attribution for Graph Neural Networks - NIPS

Interpretability of machine learning models is critical to scientific understanding, AI safety, as well as debugging. Attribution is one approach to ...

Interpretable Graph Neural Networks for Connectome-Based Brain ...

•Interpretable models on brain networks are vital. Graph Neural Networks (GNNs). •GNNs have emerged and proved its power for analyzing graph-structured data.

Interpretable Graph Neural Networks for Heterogeneous Tabular Data

Interpretable graph neural networks (XGNNs ) are widely adopted in various scientific applications involving graph-structured data. Existing ...

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

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

A Demonstration of Interpretability Methods for Graph Neural Networks

F. Baldassarre and H. Azizpour. 2019. Explainability Techniques for Graph Convolutional Networks. In ICML Workshops, 2019 Workshop on Learning and Reasoning ...

An Interpretable Graph Neural Network Framework for Brain ...

Interpretable brain network models for disease prediction are of great value for the advancement of neuroscience. GNNs are promising to model.

Explanations for Graph Neural Networks via Layer Analysis

Abstract. Like many deep learning models, graph neural networks (GNNs) are regarded as black boxes and lack interpretability. Therefore, it is difficult for ...

awesome-graph-explainability-papers/README.md at main - GitHub

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

Track: DL: Graph Neural Networks

Interpretable graph learning is in need as many scientific applications depend on learning models to collect insights from graph-structured data. Previous works ...

Toward Interpretable Graph Neural Networks via Concept Matching ...

Graph Neural Networks have achieved notable success, yet explaining their rationales remains a challenging problem. Existing methods, including post-hoc and ...

Interpretable Graph Neural Networks for Tabular Data

We propose an approach, called IGNNet (Interpretable Graph Neural Network for tabular data), which constrains the learning algorithm to produce ...

Interpretable Graph Neural Networks for Connectome-Based Brain ...

The authors proposed an interpretable brain network-oriented framework, in which a GNN is used to extract embeddings of ROIs from the brain MRI images and an ...

KerGNNs: Interpretable Graph Neural Networks with Graph Kernels

Most GNNs are based on Message Passing Neural Network (MPNN) frameworks. However, recent studies show that MPNNs can not exceed the power of the ...

Quantifying uncertainty in graph neural network explanations

Explaining the prediction of deep graph models, e.g., Graph Neural Networks (GNNs), is crucial for enhancing the model interpretability and ...

Interpreting Graph Neural Networks with Myerson Values for ...

Abstract. Here we introduce a novel method to interpret the predictions of graph neural networks (GNNs) based on Myerson values from cooperative ...