In this paper, we propose a versatile graph inference framework for learning from graph signals corrupted by exponential family noise. Our framework generalizes previous methods from continuous smooth ...

Graph-based semi-supervised learning (GSSL) has long been a research focus. Traditional methods are generally shallow learners, based on the cluster assumption.

Our results demonstrate that the proposed method significantly outperforms traditional machine learning and convolution neural network approaches, highlighting its effectiveness in large-scale ...