2.0.2
版本发布时间: 2021-10-26 20:41:58
pyg-team/pytorch_geometric最新发布版本:2.5.3(2024-04-19 19:37:44)
A new minor version release, including further bugfixes, official PyTorch 1.10 support, as well as additional features and operators:
Features
- Added video tutorials and Colabs from the PyTorch Geometric Tutorial project (thanks to @AntonioLonga)
- Added the
GraphMultisetTransformer
operator (thanks to @JinheonBaek) - Added the
PointTransformerConv
operator (thanks to @QuanticDisaster) - Added the
HEATConv
operator (thanks to @Xiaoyu006) - Added the
PNA
GNN model (thanks to @RBendias) - Added the
AddMetaPaths
transform, which will add additional edge types to aHeteroData
object based on a list of metapaths (thanks to @wsad1) - Added the
Data.to_heterogeneous
method to allow for the conversion fromData
toHeteroData
objects - Added the
AttributedGraphDataset
, containing a variety of attributes graphs - Added the
Airports
datasets - Added the
structured_negative_sampling_feasible
method, which checks ifstructured_negative_sampling
is feasible (thanks to @WuliangHuang) -
GATConv
can now make use of multi-dimensional edge features to compute attention scores (thanks to @dongkwan-kim) -
RandomNodeSplit
andRandomLinkSplit
now supportHeteroData
as input -
MessagePassing
inference can now be sped up via thedecomposed_layers
argument (thanks to @ZhouAo-ZA) -
negative_sampling
andbatched_negative_sampling
now support negative sampling in bipartite graphs -
HeteroConv
now supports the inclusion of arbitrary node-level or edge-level information for the underlyingMessagePassing
operators -
GNNExplainer
now supports multiple node-level masks and explaining regression problems (thanks to @gregorkrz)
Minor Changes
-
Data.to_homogeneous
will now addnode_type
information to the homogeneousData
object -
GINEConv
now allows to transform edge features automatically in case their dimensionalities do not match (thanks to @CaypoH) -
OGB_MAG
will now addnode_year
information to paper nodes -
Entities
datasets do now allow the processing ofHeteroData
objects via thehetero=True
option -
Batch
objects can now be batched together to form super batches - Added heterogeneous graph support for
Center
,Constant
andLinearTransformation
transformations -
HeteroConv
now allows to return "stacked" embeddings - The
batch
vector of aBatch
object will now be initialized on the GPU in case other attributes are held in GPU memory
Bugfixes
- Fixed the
num_neighbors
argument ofNeighborLoader
in order to specify an edge-type specific number of neighbors - Fixed the
collate
policy of lists of integers/strings to return nested lists - Fixed the
Delaunay
transformation in case theface
attribute is not present in the data - Fixed the
TGNMemory
module to only read from the latest update (thanks to @cwh104504) - Fixed the
pickle.PicklingError
whenBatch
objects are used in atorch.multiprocessing.manager.Queue()
(thanks to @RasmusOrsoe) - Fixed an issue with
_parent
state changing after pickling ofData
objects (thanks to @zepx) - Fixed the
ToUndirected
transformation in case the number of edges and nodes are equal (thanks to @lmkmkrcc) - Fixed the
from_networkx
routine in case node-level and edge-level features share the same names - Removed the
num_nodes
warning when creatingPairData
objects - Fixed the initialization of the
GeneralMultiLayer
module in GraphGym (thanks to @fjulian) - Fixed custom model registration in GraphGym
- Fixed a clash in the
run_dir
naming of GraphGym (thanks to @fjulian) - Includes a fix to prevent a GraphGym crash in case ROC-score is undefined (thanks to @fjulian)
- Fixed the
Batch.from_data_list
routine on dataset slices (thanks to @dtortorella) - Fixed the
MetaPath2Vec
model in case there exists isolated nodes - Fixed
torch_geometric.utils.coalesce
with CUDA tensors