Support SparseTensor label in LightGCN (#5046)

* fix the bug of models/lightgcn when edge_indx is an instance of SparseTensor in forward method

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update CHANGELOG.md

* Update torch_geometric/nn/models/lightgcn.py

Co-authored-by: Matthias Fey <matthias.fey@tu-dortmund.de>

* Update CHANGELOG.md

* Update lightgcn.py

drop all tensor.is_sparse

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* update

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Matthias Fey <matthias.fey@tu-dortmund.de>

CHANGELOG.md

@@ -5,6 +5,7 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
 
 ## [2.0.5] - 2022-MM-DD
 ### Added
+- Support `SparseTensor` as edge label in `LightGCN` (#[5046](https://github.com/pyg-team/pytorch_geometric/issues/5046))
 - Added support for `BasicGNN` models within `to_hetero` ([#5091](https://github.com/pyg-team/pytorch_geometric/pull/5091))
 - Added support for computing weighted metapaths in `AddMetapaths` ([#5049](https://github.com/pyg-team/pytorch_geometric/pull/5049))
 - Added inference benchmark suite ([#4915](https://github.com/pyg-team/pytorch_geometric/pull/4915))

torch_geometric/nn/models/lightgcn.py

@@ -5,6 +5,7 @@
 from torch import Tensor
 from torch.nn import Embedding, ModuleList
 from torch.nn.modules.loss import _Loss
+from torch_sparse import SparseTensor
 
 from torch_geometric.nn.conv import LGConv
 from torch_geometric.typing import Adj, OptTensor
@@ -110,7 +111,10 @@ def forward(self, edge_index: Adj,
                 :obj:`edge_index` will be used instead. (default: :obj:`None`)
         """
         if edge_label_index is None:
-            edge_label_index = edge_index
+            if isinstance(edge_index, SparseTensor):
+                edge_label_index = torch.stack(edge_index.coo()[:2], dim=0)
+            else:
+                edge_label_index = edge_index
 
         out = self.get_embedding(edge_index)