Interpretable Graph Neural Network

Interpretable Graph Neural Networks (IGNNs) aim to improve the transparency and understandability of graph neural networks, which are powerful but often "black box" models. Current research focuses on developing novel architectures and algorithms that generate explanations alongside predictions, often by incorporating attention mechanisms, causal inference, or graph kernel methods to highlight important features and subgraphs. This work is significant because it addresses the critical need for trust and accountability in applications of GNNs across diverse fields, including neuroscience, healthcare, and materials science, where understanding model decisions is crucial.

Papers

November 5, 2024

SurfGNN: A robust surface-based prediction model with interpretability for coactivation maps of spatial and cortical features
Zhuoshuo Li (1), Jiong Zhang (2), Youbing Zeng (1), Jiaying Lin (1), Dan Zhang (3), Jianjia Zhang (1), Duan Xu (4), Hosung Kim (5), Bingguang Liu (6), Mengting Liu (1) ((1) Department of Biomedical Engineering, Sun Yat-sen University, Shenzhen, China, (2) Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, China, (3) School of Cyber Science and Engineering, Ningbo University of Technology, Ningbo, China, (4) Department of Radiology, School of Medicine, University of California San Francisco, San Francisco, CA, USA, (5) USC Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine of USC, University of Southern California, Los Angeles, CA, USA, (6) Department of Radiology, Shenzhen Maternity and Child Healthcare Hospital, Shenzhen, China)
Inherent Interpretability Predictive Model Brain Age Activation Map Cortical Surface Interpretable Graph Neural Network

August 26, 2024

Integrated Brain Connectivity Analysis with fMRI, DTI, and sMRI Powered by Interpretable Graph Neural Networks
Gang Qu, Ziyu Zhou, Vince D. Calhoun, Aiying Zhang, Yu-Ping Wang
Functional Magnetic Resonance Imaging Functional Connectivity Multi Modality Imaging Human Connectome Project Connectivity Pattern Brain Connectivity Diffusion Tensor Imaging Interpretable Graph Neural Network

August 14, 2024

Interpretable Graph Neural Networks for Heterogeneous Tabular Data
Amr Alkhatib, Henrik Boström
Black Box Model Heterogeneous Data Feature Attribution Heterogeneous Tabular Data Interpretable Graph Neural Network

July 2, 2024

Unveiling Global Interactive Patterns across Graphs: Towards Interpretable Graph Neural Networks
Yuwen Wang, Shunyu Liu, Tongya Zheng, Kaixuan Chen, Mingli Song
Graph Neural Network Graph Drawing Graph Classification Subgraph Explanation Interpretable Graph Neural Network Interactive Visual Pattern

June 12, 2024

How Interpretable Are Interpretable Graph Neural Networks?
Yongqiang Chen, Yatao Bian, Bo Han, James Cheng
Graph Neural Network Interpretable Way Subgraph Explanation Interpretable Graph Interpretable Graph Neural Network

May 29, 2024

SIG: Efficient Self-Interpretable Graph Neural Network for Continuous-time Dynamic Graphs
Lanting Fang, Yulian Yang, Kai Wang, Shanshan Feng, Kaiyu Feng, Jie Gui, Shuliang Wang, Yew-Soon Ong
Causal Inference Dynamic Graph Causal Explanation Continuous Time Dynamic Graph Interpretable Graph Neural Network

February 7, 2024

Incorporating Retrieval-based Causal Learning with Information Bottlenecks for Interpretable Graph Neural Networks
Jiahua Rao, Jiancong Xie, Hanjing Lin, Shuangjia Zheng, Zhen Wang, Yuedong Yang
Graph Neural Network Information Bottleneck Causal Learning Subgraph Explanation Graph Information Bottleneck Interpretable Graph Neural Network

August 17, 2023

Interpretable Graph Neural Networks for Tabular Data
Amr Alkhatib, Sofiane Ennadir, Henrik Boström, Michalis Vazirgiannis
Graph Neural Network Representation Learning Tabular Data Interpretable Model Interpretable Graph Neural Network

May 17, 2023

Interpretable Graph Networks Formulate Universal Algebra Conjectures
Francesco Giannini, Stefano Fioravanti, Oguzhan Keskin, Alisia Maria Lupidi, Lucie Charlotte Magister, Pietro Lio, Pietro Barbiero
Inherent Interpretability Topological Representation Explainability Problem Universal Algebra Interpretable Graph Neural Network

June 30, 2022

Interpretable Graph Neural Networks for Connectome-Based Brain Disorder Analysis
Hejie Cui, Wei Dai, Yanqiao Zhu, Xiaoxiao Li, Lifang He, Carl Yang
Graph Neural Network Deep Model Brain Network Human Brain Interpretable Graph Neural Network

April 27, 2022

Interpretable Graph Convolutional Network of Multi-Modality Brain Imaging for Alzheimer's Disease Diagnosis
Houliang Zhou, Lifang He, Yu Zhang, Li Shen, Brian Chen
Alzheimer'S Disease Brain Connectivity Interpretable Graph Neural Network Class Activation Mapping

March 29, 2022

OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks
Wanyu Lin, Hao Lan, Hao Wang, Baochun Li
Causal Graph Explanation Generation Latent Causal Causal Explanation Subgraph Explanation Interpretable Graph Neural Network Causal Hierarchy

January 30, 2022

Discovering Invariant Rationales for Graph Neural Networks
Ying-Xin Wu, Xiang Wang, An Zhang, Xiangnan He, Tat-Seng Chua
Graph Neural Network Inherent Interpretability Causal Pattern Interpretable Graph Neural Network

January 3, 2022

KerGNNs: Interpretable Graph Neural Networks with Graph Kernels
Aosong Feng, Chenyu You, Shiqiang Wang, Leandros Tassiulas
Graph Neural Network Graph Classification Graph Kernel Graph Filter Interpretable Graph Neural Network

Interpretable Graph Neural Network

Papers

SurfGNN: A robust surface-based prediction model with interpretability for coactivation maps of spatial and cortical features

Integrated Brain Connectivity Analysis with fMRI, DTI, and sMRI Powered by Interpretable Graph Neural Networks

Interpretable Graph Neural Networks for Heterogeneous Tabular Data

Unveiling Global Interactive Patterns across Graphs: Towards Interpretable Graph Neural Networks

How Interpretable Are Interpretable Graph Neural Networks?

SIG: Efficient Self-Interpretable Graph Neural Network for Continuous-time Dynamic Graphs

Incorporating Retrieval-based Causal Learning with Information Bottlenecks for Interpretable Graph Neural Networks

Interpretable Graph Neural Networks for Tabular Data

Interpretable Graph Networks Formulate Universal Algebra Conjectures

Interpretable Graph Neural Networks for Connectome-Based Brain Disorder Analysis

Interpretable Graph Convolutional Network of Multi-Modality Brain Imaging for Alzheimer's Disease Diagnosis

OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks

Discovering Invariant Rationales for Graph Neural Networks

KerGNNs: Interpretable Graph Neural Networks with Graph Kernels