graphvelo.graph_velocity.GraphVelo.train

GraphVelo.train(a=1, b=10, r=1, loss_func=None, transition_matrix=None, softmax_adjusted=False)

Train the GraphVelo model by learning the phi coefficients in tangent space.

Parameters:

a, b, r: Weights for the loss function components. loss_func (str): Loss function type; defaults to ‘linear’ if approx is True, else ‘log’. transition_matrix: Optionally provided transition matrix; if not provided, it is computed. softmax_adjusted (bool): Flag for adjusting the softmax in the correlation kernel.