Parametric umap worse than umap

I carried out experiments with parametric umap and umap

umap

1. Clusters spread out throughout the entire space.
2. There are datapoints in between the clusters, that are representing the transition from one cluster to another {which I can notice in the data}

parametric umap:

1. The final map has few dense clusters that are present only in a small region
2. I can't observe any transitions

I used the default parameters for both umap and parametric umap.
I tried different model architectures.
I tried tuning the hyper-parameters for training such as batch size and number of epochs

Is there any reason that we are not able to get a good performance from p-umap similar to that of the umap ?

Start with the parametric UMAP entry point and compare it with standard UMAP using the default parameters described in the report. Reproduce the dense-cluster and missing-transition behavior, then inspect how model architecture, batch size, and epoch settings affect training. Done means identifying a reproducible cause or documenting the conditions under which both methods differ.