In the current implementation, generating multiple higher-order models for different max. k requires to compute the temporal event graph multiple times, which is the main bottleneck in the computation.
For scenarios where we want to generate multiple multi-order models from the same temporal graph, it would be useful to generate the tempoal event graph only once for a given delta, and then reuse it. This could be done by adding a function MultiOderModel.from_temporal_event_graph, which would allow to manually generate the temporal event graph once using the function in pp.temporal.
In the current implementation, generating multiple higher-order models for different max. k requires to compute the temporal event graph multiple times, which is the main bottleneck in the computation.
For scenarios where we want to generate multiple multi-order models from the same temporal graph, it would be useful to generate the tempoal event graph only once for a given delta, and then reuse it. This could be done by adding a function
MultiOderModel.from_temporal_event_graph, which would allow to manually generate the temporal event graph once using the function inpp.temporal.