Torch_geometric , HeteroData , GNN, multi-dimensional features with varying dimensions

Hi
I am experimenting with torch_geometric and HeteroData et al…

following specifically MovieLens link regression example…

In the example ‘user_features’ are one-dimensional…ie, each user is represented by an one-dimensional vector…and HeteroData is created and all fine…

My question is WHAT IF my user_features are multi and different dimensional…ie, each user is represented by a matrix and these matrices have different dimensions…

eg: I have a list of ‘Data’ objects as following…

tmp_users = [Data(x=[28, 36]),
Data(x=[22, 36]),
Data(x=[32, 36]),
Data(x=[30, 36]),
Data(x=[35, 36]
]

How do I use this ‘tmp_users’ to create the ‘user’ Nodes/features as in the MovieLens example…
ie,

data = HeteroData()

data[‘user’].x = ???

data[‘movies’].x=…

Help much appreciated…

Regards