Question regarding sparse matrices

[KukumavMozolo]

Hi there, i stumbled over the problem that the algorithm try's to allocate more memory than i currently have. This happens in this implementation and the sklearn implementation of hdbscan and i found the following lines of code here.

        if issparse(X) or metric not in FAST_METRICS:
            # We can't do much with sparse matrices ...

So apparently it is not possible to reduce memory consumption if the dataset is sparse and i am trying to understand why that is.
Maybe somebody could elaborate?