Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

More tests for column split and vertical federated learning (#8985)

Browse Source 
Added some more tests for the learner and fit_stump, for both column-wise distributed learning and vertical federated learning.

Also moved the `IsRowSplit` and `IsColumnSplit` methods from the `DMatrix` to the `MetaInfo` since in some places we only have access to the `MetaInfo`. Added a new convenience method `IsVerticalFederatedLearning`.

Some refactoring of the testing fixtures.
This commit is contained in:
Rong Ou
2023-03-28 01:40:26 -07:00
committed by GitHub
parent 401ce5cf5e
commit ff26cd3212
18 changed files with 212 additions and 94 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/data/iterative_dmatrix.cc
View File

@@ -213,7 +213,7 @@ void IterativeDMatrix::InitFromCPU(DataIterHandle iter_handle, float missing,
SyncFeatureType(&h_ft);
p_sketch.reset(new common::HostSketchContainer{
batch_param_.max_bin, h_ft, column_sizes, !proxy->Info().group_ptr_.empty(),
proxy->IsColumnSplit(), ctx_.Threads()});
proxy->Info().IsColumnSplit(), ctx_.Threads()});
}
HostAdapterDispatch(proxy, [&](auto const& batch) {
proxy->Info().num_nonzero_ = batch_nnz[i];