Localized MIMO graph convolutions (LMGCs) generalize many linear message-passing GNNs and are provably injective and produce linearly independent representations for almost every edge weight choice.
Beyond low-frequency information in graph convolutional networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
What Can We Learn From MIMO Graph Convolutions?
Localized MIMO graph convolutions (LMGCs) generalize many linear message-passing GNNs and are provably injective and produce linearly independent representations for almost every edge weight choice.