Trustworthy Graph Neural Networks: Aspects, Methods and Trends

arXiv:2205.07424v2 Announce Type: replace
Abstract: Graph neural networks (GNNs) have emerged as a series of competent graph learning methods for diverse real-world scenarios, ranging from daily applications like recommendation systems and question answering to cutting-edge technologies such as drug discovery in life sciences and n-body simulation in astrophysics. However, task performance is not the only requirement for GNNs. Performance-oriented GNNs have exhibited potential adverse effects like vulnerability to adversarial attacks, unexplainable discrimination against disadvantaged groups, or excessive resource consumption in …

abstract applications arxiv astrophysics cs.ai cs.lg daily discovery diverse drug discovery edge edge technologies gnns graph graph learning graph neural networks life life sciences networks neural networks performance question question answering recommendation recommendation systems series simulation systems technologies trends trustworthy type world