GEGCN improves graph classification by using LSTM to capture dynamic sequences from discrete Ricci flow and infusing those representations into a graph convolutional network.
Adaptive graph diffusion net- works: compact and expressive GNNs with large receptive fields
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Geometric Evolution Graph Convolutional Networks: Enhancing Graph Representation Learning via Ricci Flow
GEGCN improves graph classification by using LSTM to capture dynamic sequences from discrete Ricci flow and infusing those representations into a graph convolutional network.