The authors propose DCN and PDCN, new GNN architectures using causal graph filters for convolutional learning on DAGs, with established equivariance properties and competitive empirical performance.
Graph signal processing: Overview, challenges, and ap- plications,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
eess.SP 3verdicts
UNVERDICTED 3representative citing papers
Introduces coarse and fine feature-graph alignment notions to enable subgraph sampling that preserves Laplacian trace and spectral properties for improved GNN transferability without relying on complete graph structure.
LGLMS unifies line graph transformation with LMS adaptive filters for online prediction of time-varying signals on graph edges.
citing papers explorer
-
Directed Acyclic Graph Convolutional Networks
The authors propose DCN and PDCN, new GNN architectures using causal graph filters for convolutional learning on DAGs, with established equivariance properties and competitive empirical performance.
-
Sampling Transferable Graph Neural Networks with Limited Graph Information
Introduces coarse and fine feature-graph alignment notions to enable subgraph sampling that preserves Laplacian trace and spectral properties for improved GNN transferability without relying on complete graph structure.
-
Adaptive Spatio-temporal Estimation on the Graph Edges via Line Graph Transformation
LGLMS unifies line graph transformation with LMS adaptive filters for online prediction of time-varying signals on graph edges.