IEEE5d
Energy-Propagation Graph Neural Networks for Enhanced Out-of-Distribution Fault Analysis in Intelligent Construction Machinery Systems
This article introduces the energy-driven graph neural OOD (EGN-OOD) detector, a novel framework designed to address the complexities of OOD data in dynamic Internet of Things (IoT) environments. By ...
IEEE1mon
Scalable and Effective Graph Neural Networks Via Trainable Random Walk Sampling
which easily fails on heterophilous graphs. In this paper, we propose the random walk extension for those message-passing based GNNs, enriching them with spectral powers. We prove that our random walk ...