RandomLinkSplit
and LinkNeighborLoader
seem to sample ordinary subgraph or graph with Isolated node in directed heterogeneous graph
#9552
Unanswered
0zero000zero0
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
It seems that
RandomLinkSplit
andLinkNeighborLoader
often sample ordinary subgraph in directed heterogeneous graph.I don't it is a bug or something wrong with my code.
Here I have a directed heterogeneous graph , and use
RandomLinkSplit
to split data as train data and test data:The train data as follow:
Then I use
LinkNeighborLoader
to sample and load data to train my model:As you can see, there are some nodes but aren not edges in the subgraph . When I use a larger
num_neighbors
such asnum_neighbors=[5,2]
, the number of edge is not zero , but there is isolated node:I tried different parameter combination (such as
add_negative_train_samples
,disjoint_train_ratio
,neg_sampling_ratio
,num_neighbors
) , but still don't work.I am curious about the process and principles of sampling
I gauss the it is a bug because of approximate way of sampling.
Here are my equipment information:
operating system:Window11 23H2
python : 3.12.3
related packes verson:
torch=2.2.1 cu118
torch_cluster=1.6.3 pt22cu118
torch_geometric = 2.5.3
torch_scatter =2.1.2 pt22cu118
torch_sparse =0.6.18 pt22cu118
torch_spline_conv =1.2.2 pt22cu118
Beta Was this translation helpful? Give feedback.
All reactions