no code implementations • 4 Mar 2023 • John Shi, Jose M. F. Moura
The paper presents the graph signal processing (GSP) companion model that naturally replicates the basic tenets of classical signal processing (DSP) for GSP.
no code implementations • 25 Mar 2022 • John Shi, Jose M. F. Moura
This paper introduces a $\textit{canonical}$ graph signal model defined by a $\textit{canonical}$ graph and a $\textit{canonical}$ shift, the $\textit{companion}$ graph and the $\textit{companion}$ shift.
no code implementations • 19 Mar 2021 • John Shi, Jose M. F. Moura
This paper shows that in fact one can develop a unified graph signal sampling theory with analogous interpretations in both domains just like sampling in traditional DSP.
no code implementations • 16 Dec 2020 • Lavender Yao Jiang, John Shi, Mark Cheung, Oren Wright, José M. F. Moura
Graph neural networks (GNNs) extend convolutional neural networks (CNNs) to graph-based data.
no code implementations • 4 Aug 2020 • Mark Cheung, John Shi, Oren Wright, Lavender Y. Jiang, Xujin Liu, José M. F. Moura
Deep learning, particularly convolutional neural networks (CNNs), have yielded rapid, significant improvements in computer vision and related domains.
no code implementations • 7 Apr 2020 • Mark Cheung, John Shi, Lavender Yao Jiang, Oren Wright, José M. F. Moura
Graph convolutional neural networks (GCNNs) are a powerful extension of deep learning techniques to graph-structured data problems.