Graph-level pseudotime plus neural stochastic differential equations applied to 23 mouse retinas reports sensitive pathways, stability rankings, and a step-4 bifurcation, but the trajectory encodes the severity labels used to construct it.
For the hyperparameters, we let the hidden dimension of the GCN model as 64 and the dropout ratio as 0.5 with the learning rate as 1e−3 and weight decay as 1e−4
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Graph Pseudotime Analysis and Neural Stochastic Differential Equations for Analyzing Retinal Degeneration Dynamics and Beyond
Graph-level pseudotime plus neural stochastic differential equations applied to 23 mouse retinas reports sensitive pathways, stability rankings, and a step-4 bifurcation, but the trajectory encodes the severity labels used to construct it.