3 papers
cs.LG2024
Adaptive Least Mean pth Power Graph Neural Networks
Yi Yan, Changran Peng, Ercan E. Kuruoglu
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…
cs.LG2024
Binarized Simplicial Convolutional Neural Networks
Yi Yan, Ercan E. Kuruoglu
Graph Neural Networks have a limitation of solely processing features on graph nodes, neglecting data on high-dimensional structures such as edges and triangles. Simplicial Convolu…
cs.SI2024
Adaptive Joint Estimation of Temporal Vertex and Edge Signals
Yi Yan, Tian Xie, Ercan E. Kuruoglu
The adaptive estimation of coexisting temporal vertex (node) and edge signals on graphs is a critical task when a change in edge signals influences the temporal dynamics of the ver…