Adaptive Least Mean pth Power Graph Neural Networks

arXiv:2405.04111v1 Announce Type: new
Abstract: In the presence of impulsive noise, and missing observations, accurate online prediction of time-varying graph signals poses a crucial challenge in numerous application domains. We propose the Adaptive Least Mean $p^{th}$ Power Graph Neural Networks (LMP-GNN), a universal framework combining adaptive filter and graph neural network for online graph signal estimation. LMP-GNN retains the advantage of adaptive filtering in handling noise and missing observations as well as the online update capability. The incorporated graph neural …

abstract application arxiv challenge cs.lg domains eess.sp filter framework gnn graph graph neural network graph neural networks least mean network networks neural network neural networks noise power prediction type universal