Trustworthy graph neural networks: Aspects, methods, and trends

H Zhang, B Wu, X Yuan, S Pan, H Tong… - Proceedings of the …, 2024 - ieeexplore.ieee.org
Graph neural networks (GNNs) have emerged as a series of competent graph learning
methods for diverse real-world scenarios, ranging from daily applications such as …

Dag matters! gflownets enhanced explainer for graph neural networks

W Li, Y Li, Z Li, J Hao, Y Pang - arxiv preprint arxiv:2303.02448, 2023 - arxiv.org
Uncovering rationales behind predictions of graph neural networks (GNNs) has received
increasing attention over the years. Existing literature mainly focus on selecting a subgraph …

Explaining graph neural networks via structure-aware interaction index

N Bui, HT Nguyen, VA Nguyen, R Ying - arxiv preprint arxiv:2405.14352, 2024 - arxiv.org
The Shapley value is a prominent tool for interpreting black-box machine learning models
thanks to its strong theoretical foundation. However, for models with structured inputs, such …

Factorized explainer for graph neural networks

R Huang, F Shirani, D Luo - Proceedings of the AAAI conference on …, 2024 - ojs.aaai.org
Graph Neural Networks (GNNs) have received increasing attention due to their ability to
learn from graph-structured data. To open the black-box of these deep learning models, post …