I can't figure out how to create the data because if I use Heterogeneous I can get the 1st node and determine the relationship between them

[ad7090]

Suppose we have 10 million nodes, each of which has an edge sequence
for example,
node one with 4 edges, node 2 with 100 edges, etc.

Each node will have edge indexes that are practically the same edge

Node 3: with node 1, 2, 4, 5...
and each node is in the same order

I can't figure out how to create the data because if I use Heterogeneous I can get the 1st node and determine the relationship between them

below code :

from torch_geometric.data import HeteroData
data = HeteroData()

data['paper'].x = ... # [num_papers, num_features_paper]
data['author'].x = ... # [num_authors, num_features_author]
data['institution'].x = ... # [num_institutions, num_features_institution]
data['field_of_study'].x = ... # [num_field, num_features_field]

data['paper', 'cites', 'paper'].edge_index = ... # [2, num_edges_cites]
data['author', 'writes', 'paper'].edge_index = ... # [2, num_edges_writes]
data['author', 'affiliated_with', 'institution'].edge_index = ... # [2, num_edges_affiliated]
data['paper', 'has_topic', 'field_of_study'].edge_index = ... # [2, num_edges_topic]

data['paper', 'cites', 'paper'].edge_attr = ... # [num_edges_cites, num_features_cites]
data['author', 'writes', 'paper'].edge_attr = ... # [num_edges_writes, num_features_writes]
data['author', 'affiliated_with', 'institution'].edge_attr = ... # [num_edges_affiliated, num_features_affiliated]
data['paper', 'has_topic', 'field_of_study'].edge_attr = ... # [num_edges_topic, num_features_topic]

If I use homegenues, the size of the hand increases
because, for example,
node 1 has 4 edges, but node 100 has, for example, 50 edges
in this case i have use Onhot format Which doesn't make sense at all because the amount of information would be overwhelming.