dmlc--dgl
9699b93136
* Update from master (#4584)
* [Example][Refactor] Refactor graphsage multigpu and full-graph example (#4430)
* Add refactors for multi-gpu and full-graph example
* Fix format
* Update
* Update
* Update
* [Cleanup] Remove async_transferer (#4505)
* Remove async_transferer
* remove test
* Remove AsyncTransferer
Co-authored-by: Xin Yao <xiny@nvidia.com>
Co-authored-by: Xin Yao <yaox12@outlook.com>
* [Cleanup] Remove duplicate entries of CUB submodule (issue# 4395) (#4499)
* remove third_part/cub
* remove from third_party
Co-authored-by: Israt Nisa <nisisrat@amazon.com>
Co-authored-by: Xin Yao <xiny@nvidia.com>
* [Bug] Enable turn on/off libxsmm at runtime (#4455)
* enable turn on/off libxsmm at runtime by adding a global config and related API
Co-authored-by: Ubuntu <ubuntu@ip-172-31-19-194.ap-northeast-1.compute.internal>
* [Feature] Unify the cuda stream used in core library (#4480)
* Use an internal cuda stream for CopyDataFromTo
* small fix white space
* Fix to compile
* Make stream optional in copydata for compile
* fix lint issue
* Update cub functions to use internal stream
* Lint check
* Update CopyTo/CopyFrom/CopyFromTo to use internal stream
* Address comments
* Fix backward CUDA stream
* Avoid overloading CopyFromTo()
* Minor comment update
* Overload copydatafromto in cuda device api
Co-authored-by: xiny <xiny@nvidia.com>
* [Feature] Added exclude_self and output_batch to knn graph construction (Issues #4323 #4316) (#4389)
* * Added "exclude_self" and "output_batch" options to knn_graph and segmented_knn_graph
* Updated out-of-date comments on remove_edges and remove_self_loop, since they now preserve batch information
* * Changed defaults on new knn_graph and segmented_knn_graph function parameters, for compatibility; pytorch/test_geometry.py was failing
* * Added test to ensure dgl.remove_self_loop function correctly updates batch information
* * Added new knn_graph and segmented_knn_graph parameters to dgl.nn.KNNGraph and dgl.nn.SegmentedKNNGraph
* * Formatting
* * Oops, I missed the one in segmented_knn_graph when I fixed the similar thing in knn_graph
* * Fixed edge case handling when invalid k specified, since it still needs to be handled consistently for tests to pass
* Fixed context of batch info, since it must match the context of the input position data for remove_self_loop to succeed
* * Fixed batch info resulting from knn_graph when output_batch is true, for case of 3D input tensor, representing multiple segments
* * Added testing of new exclude_self and output_batch parameters on knn_graph and segmented_knn_graph, and their wrappers, KNNGraph and SegmentedKNNGraph, into the test_knn_cuda test
* * Added doc comments for new parameters
* * Added correct handling for uncommon case of k or more coincident points when excluding self edges in knn_graph and segmented_knn_graph
* Added test cases for more than k coincident points
* * Updated doc comments for output_batch parameters for clarity
* * Linter formatting fixes
* * Extracted out common function for test_knn_cpu and test_knn_cuda, to add the new test cases to test_knn_cpu
* * Rewording in doc comments
* * Removed output_batch parameter from knn_graph and segmented_knn_graph, in favour of always setting the batch information, except in knn_graph if x is a 2D tensor
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com>
* [CI] only known devs are authorized to trigger CI (#4518)
* [CI] only known devs are authorized to trigger CI
* fix if author is null
* add comments
* [Readability] Auto fix setup.py and update-version.py (#4446)
* Auto fix update-version
* Auto fix setup.py
* Auto fix update-version
* Auto fix setup.py
* [Doc] Change random.py to random_partition.py in guide on distributed partition pipeline (#4438)
* Update distributed-preprocessing.rst
* Update
Co-authored-by: Ubuntu <ubuntu@ip-172-31-9-26.ap-northeast-1.compute.internal>
* fix unpinning when tensoradaptor is not available (#4450)
* [Doc] fix print issue in tutorial (#4459)
* [Example][Refactor] Refactor RGCN example (#4327)
* Refactor full graph entity classification
* Refactor rgcn with sampling
* README update
* Update
* Results update
* Respect default setting of self_loop=false in entity.py
* Update
* Update README
* Update for multi-gpu
* Update
* [doc] fix invalid link in user guide (#4468)
* [Example] directional_GSN for ogbg-molpcba (#4405)
* version-1
* version-2
* version-3
* update examples/README
* Update .gitignore
* update performance in README, delete scripts
* 1st approving review
* 2nd approving review
Co-authored-by: Mufei Li <mufeili1996@gmail.com>
* Clarify the message name, which is 'm'. (#4462)
Co-authored-by: Ubuntu <ubuntu@ip-172-31-34-29.ap-northeast-1.compute.internal>
Co-authored-by: Rhett Ying <85214957+Rhett-Ying@users.noreply.github.com>
* [Refactor] Auto fix view.py. (#4461)
Co-authored-by: Ubuntu <ubuntu@ip-172-31-34-29.ap-northeast-1.compute.internal>
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com>
* [Example] SEAL for OGBL (#4291)
* [Example] SEAL for OGBL
* update index
* update
* fix readme typo
* add seal sampler
* modify set ops
* prefetch
* efficiency test
* update
* optimize
* fix ScatterAdd dtype issue
* update sampler style
* update
Co-authored-by: Quan Gan <coin2028@hotmail.com>
* [CI] use https instead of http (#4488)
* [BugFix] fix crash due to incorrect dtype in dgl.to_block() (#4487)
* [BugFix] fix crash due to incorrect dtype in dgl.to_block()
* fix test failure in TF
* [Feature] Make TensorAdapter Stream Aware (#4472)
* Allocate tensors in DGL's current stream
* make tensoradaptor stream-aware
* replace TAemtpy with cpu allocator
* fix typo
* try fix cpu allocation
* clean header
* redirect AllocDataSpace as well
* resolve comments
* [Build][Doc] Specify the sphinx version (#4465)
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com>
* reformat
* reformat
* Auto fix update-version
* Auto fix setup.py
* reformat
* reformat
Co-authored-by: Ubuntu <ubuntu@ip-172-31-34-29.ap-northeast-1.compute.internal>
Co-authored-by: Rhett Ying <85214957+Rhett-Ying@users.noreply.github.com>
Co-authored-by: Mufei Li <mufeili1996@gmail.com>
Co-authored-by: Ubuntu <ubuntu@ip-172-31-9-26.ap-northeast-1.compute.internal>
Co-authored-by: Xin Yao <xiny@nvidia.com>
Co-authored-by: Chang Liu <chang.liu@utexas.edu>
Co-authored-by: Zhiteng Li <55398076+ZHITENGLI@users.noreply.github.com>
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com>
Co-authored-by: rudongyu <ru_dongyu@outlook.com>
Co-authored-by: Quan Gan <coin2028@hotmail.com>
* Move mock version of dgl_sparse library to DGL main repo (#4524)
* init
* Add api doc for sparse library
* support op btwn matrices with differnt sparsity
* Fixed docstring
* addresses comments
* lint check
* change keyword format to fmt
Co-authored-by: Israt Nisa <nisisrat@amazon.com>
* [DistPart] expose timeout config for process group (#4532)
* [DistPart] expose timeout config for process group
* refine code
* Update tools/distpartitioning/data_proc_pipeline.py
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com>
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com>
* [Feature] Import PyTorch's CUDA stream management (#4503)
* add set_stream
* add .record_stream for NDArray and HeteroGraph
* refactor dgl stream Python APIs
* test record_stream
* add unit test for record stream
* use pytorch's stream
* fix lint
* fix cpu build
* address comments
* address comments
* add record stream tests for dgl.graph
* record frames and update dataloder
* add docstring
* update frame
* add backend check for record_stream
* remove CUDAThreadEntry::stream
* record stream for newly created formats
* fix bug
* fix cpp test
* fix None c_void_p to c_handle
* [examples]educe memory consumption (#4558)
* [examples]educe memory consumption
* reffine help message
* refine
* [Feature][REVIEW] Enable DGL cugaph nightly CI (#4525)
* Added cugraph nightly scripts
* Removed nvcr.io//nvidia/pytorch:22.04-py3 reference
Co-authored-by: Rhett Ying <85214957+Rhett-Ying@users.noreply.github.com>
* Revert "[Feature][REVIEW] Enable DGL cugaph nightly CI (#4525)" (#4563)
This reverts commit ec171c648a.
* [Misc] Add flake8 lint workflow. (#4566)
* Add pyproject.toml for autopep8.
* Add pyproject.toml for autopep8.
* Add flake8 annotation in workflow.
* remove
* add
* clean up
Co-authored-by: Steve <ubuntu@ip-172-31-34-29.ap-northeast-1.compute.internal>
* [Misc] Try use official pylint workflow. (#4568)
* polish update_version
* update pylint workflow.
* add
* revert.
Co-authored-by: Steve <ubuntu@ip-172-31-34-29.ap-northeast-1.compute.internal>
* [CI] refine stage logic (#4565)
* [CI] refine stage logic
* refine
* refine
* remove (#4570)
Co-authored-by: Steve <ubuntu@ip-172-31-34-29.ap-northeast-1.compute.internal>
* Add Pylint workflow for flake8. (#4571)
* remove
* Add pylint.
Co-authored-by: Steve <ubuntu@ip-172-31-34-29.ap-northeast-1.compute.internal>
* [Misc] Update the python version in Pylint workflow for flake8. (#4572)
* remove
* Add pylint.
* Change the python version for pylint.
Co-authored-by: Steve <ubuntu@ip-172-31-34-29.ap-northeast-1.compute.internal>
* Update pylint. (#4574)
Co-authored-by: Steve <ubuntu@ip-172-31-34-29.ap-northeast-1.compute.internal>
* [Misc] Use another workflow. (#4575)
* Update pylint.
* Use another workflow.
Co-authored-by: Steve <ubuntu@ip-172-31-34-29.ap-northeast-1.compute.internal>
* Update pylint. (#4576)
Co-authored-by: Steve <ubuntu@ip-172-31-34-29.ap-northeast-1.compute.internal>
* Update pylint.yml
* Update pylint.yml
* Delete pylint.yml
* [Misc]Add pyproject.toml for autopep8 & black. (#4543)
* Add pyproject.toml for autopep8.
* Add pyproject.toml for autopep8.
Co-authored-by: Steve <ubuntu@ip-172-31-34-29.ap-northeast-1.compute.internal>
* [Feature] Bump DLPack to v0.7 and decouple DLPack from the core library (#4454)
* rename `DLContext` to `DGLContext`
* rename `kDLGPU` to `kDLCUDA`
* replace DLTensor with DGLArray
* fix linting
* Unify DGLType and DLDataType to DGLDataType
* Fix FFI
* rename DLDeviceType to DGLDeviceType
* decouple dlpack from the core library
* fix bug
* fix lint
* fix merge
* fix build
* address comments
* rename dl_converter to dlpack_convert
* remove redundant comments
Co-authored-by: Chang Liu <chang.liu@utexas.edu>
Co-authored-by: nv-dlasalle <63612878+nv-dlasalle@users.noreply.github.com>
Co-authored-by: Xin Yao <xiny@nvidia.com>
Co-authored-by: Xin Yao <yaox12@outlook.com>
Co-authored-by: Israt Nisa <neesha295@gmail.com>
Co-authored-by: Israt Nisa <nisisrat@amazon.com>
Co-authored-by: peizhou001 <110809584+peizhou001@users.noreply.github.com>
Co-authored-by: Ubuntu <ubuntu@ip-172-31-19-194.ap-northeast-1.compute.internal>
Co-authored-by: ndickson-nvidia <99772994+ndickson-nvidia@users.noreply.github.com>
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com>
Co-authored-by: Rhett Ying <85214957+Rhett-Ying@users.noreply.github.com>
Co-authored-by: Hongzhi (Steve), Chen <chenhongzhi.nkcs@gmail.com>
Co-authored-by: Ubuntu <ubuntu@ip-172-31-34-29.ap-northeast-1.compute.internal>
Co-authored-by: Ubuntu <ubuntu@ip-172-31-9-26.ap-northeast-1.compute.internal>
Co-authored-by: Zhiteng Li <55398076+ZHITENGLI@users.noreply.github.com>
Co-authored-by: rudongyu <ru_dongyu@outlook.com>
Co-authored-by: Quan Gan <coin2028@hotmail.com>
Co-authored-by: Vibhu Jawa <vibhujawa@gmail.com>
* [Deprecation] Dataset Attributes (#4546)
* Update
* CI
* CI
* Update
Co-authored-by: Ubuntu <ubuntu@ip-172-31-9-26.ap-northeast-1.compute.internal>
* [Example] Bug Fix (#4665)
* Update
* CI
* CI
* Update
* Update
Co-authored-by: Ubuntu <ubuntu@ip-172-31-9-26.ap-northeast-1.compute.internal>
* Update
* Update (#4724)
Co-authored-by: Ubuntu <ubuntu@ip-172-31-9-26.ap-northeast-1.compute.internal>
* change DGLHeteroGraph to DGLGraph in DOC
* revert c change
Co-authored-by: Mufei Li <mufeili1996@gmail.com>
Co-authored-by: Chang Liu <chang.liu@utexas.edu>
Co-authored-by: nv-dlasalle <63612878+nv-dlasalle@users.noreply.github.com>
Co-authored-by: Xin Yao <xiny@nvidia.com>
Co-authored-by: Xin Yao <yaox12@outlook.com>
Co-authored-by: Israt Nisa <neesha295@gmail.com>
Co-authored-by: Israt Nisa <nisisrat@amazon.com>
Co-authored-by: Ubuntu <ubuntu@ip-172-31-19-194.ap-northeast-1.compute.internal>
Co-authored-by: ndickson-nvidia <99772994+ndickson-nvidia@users.noreply.github.com>
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com>
Co-authored-by: Rhett Ying <85214957+Rhett-Ying@users.noreply.github.com>
Co-authored-by: Hongzhi (Steve), Chen <chenhongzhi.nkcs@gmail.com>
Co-authored-by: Ubuntu <ubuntu@ip-172-31-34-29.ap-northeast-1.compute.internal>
Co-authored-by: Ubuntu <ubuntu@ip-172-31-9-26.ap-northeast-1.compute.internal>
Co-authored-by: Zhiteng Li <55398076+ZHITENGLI@users.noreply.github.com>
Co-authored-by: rudongyu <ru_dongyu@outlook.com>
Co-authored-by: Quan Gan <coin2028@hotmail.com>
Co-authored-by: Vibhu Jawa <vibhujawa@gmail.com>
Co-authored-by: Ubuntu <ubuntu@ip-172-31-16-19.ap-northeast-1.compute.internal>
267 行
12 KiB
ReStructuredText
267 行
12 KiB
ReStructuredText
.. _guide_ko-minibatch-link-classification-sampler:
|
|
|
|
6.3 이웃 샘플링을 사용한 링크 예측 GNN 모델 학습하기
|
|
-----------------------------------------
|
|
|
|
:ref:`(English Version) <guide-minibatch-link-classification-sampler>`
|
|
|
|
Negative 샘플링을 사용한 이웃 샘플러 및 데이터 로더 정의하기
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
노드/에지 분류에서 사용한 이웃 샘플러를 그대로 사용하는 것이 가능하다.
|
|
|
|
.. code:: python
|
|
|
|
sampler = dgl.dataloading.MultiLayerFullNeighborSampler(2)
|
|
|
|
DGL의 :class:`~dgl.dataloading.pytorch.EdgeDataLoader` 는 링크 예측를 위한 negative 샘플 생성을
|
|
지원한다. 이를 사용하기 위해서는, negative 샘플링 함수를 제공해야한다. :class:`~dgl.dataloading.negative_sampler.Uniform` 은 uniform 샘플링을 해주는 함수이다. 에지의 각 소스 노드에 대해서,이 함수는 ``k`` 개의 negative 목적지 노드들을 샘플링한다.
|
|
|
|
아래 코드는 에지의 각 소스 노드에 대해서 5개의 negative 목적지 노드를 균등하게 선택한다.
|
|
|
|
.. code:: python
|
|
|
|
dataloader = dgl.dataloading.EdgeDataLoader(
|
|
g, train_seeds, sampler,
|
|
negative_sampler=dgl.dataloading.negative_sampler.Uniform(5),
|
|
batch_size=args.batch_size,
|
|
shuffle=True,
|
|
drop_last=False,
|
|
pin_memory=True,
|
|
num_workers=args.num_workers)
|
|
|
|
빌드인 negative 샘플러들은 :ref:`api-dataloading-negative-sampling` 에서 확인하자.
|
|
|
|
직접 만든 negative 샘플러 함수를 사용할 수도 있다. 이 함수는 원본 그래프 ``g`` 와, 미니배치 에지 ID 배열 ``eid`` 를 받아서
|
|
소스 ID 배열과 목적지 ID 배열의 쌍을 리턴해야 한다.
|
|
|
|
아래 코드 예제는 degree의 거듭제곱에 비례하는 확률 분포에 따라서 negative 목적지 노드들을 샘플링하는 custom negative 샘플러다.
|
|
|
|
.. code:: python
|
|
|
|
class NegativeSampler(object):
|
|
def __init__(self, g, k):
|
|
# caches the probability distribution
|
|
self.weights = g.in_degrees().float() ** 0.75
|
|
self.k = k
|
|
|
|
def __call__(self, g, eids):
|
|
src, _ = g.find_edges(eids)
|
|
src = src.repeat_interleave(self.k)
|
|
dst = self.weights.multinomial(len(src), replacement=True)
|
|
return src, dst
|
|
|
|
dataloader = dgl.dataloading.EdgeDataLoader(
|
|
g, train_seeds, sampler,
|
|
negative_sampler=NegativeSampler(g, 5),
|
|
batch_size=args.batch_size,
|
|
shuffle=True,
|
|
drop_last=False,
|
|
pin_memory=True,
|
|
num_workers=args.num_workers)
|
|
|
|
모델을 미니-배치 학습에 맞게 만들기
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
:ref:`guide_ko-training-link-prediction` 에서 설명한 것처럼, 링크 예측은 (positive 예제인) 에지의 점수와 존재하지 않는 에지(즉, negative 예제)의 점수를 비교하는 것을 통해서 학습될 수 있다. 에지들의 점수를 계산하기 위해서, 에지 분류/리그레션에서 사용했던 노드 representation 계산 모델을 재사용한다.
|
|
|
|
.. code:: python
|
|
|
|
class StochasticTwoLayerGCN(nn.Module):
|
|
def __init__(self, in_features, hidden_features, out_features):
|
|
super().__init__()
|
|
self.conv1 = dgl.nn.GraphConv(in_features, hidden_features)
|
|
self.conv2 = dgl.nn.GraphConv(hidden_features, out_features)
|
|
|
|
def forward(self, blocks, x):
|
|
x = F.relu(self.conv1(blocks[0], x))
|
|
x = F.relu(self.conv2(blocks[1], x))
|
|
return x
|
|
|
|
점수 예측을 위해서 확률 분포 대신 각 에지의 scalar 점수를 예측하기만 하면되기 때문에, 이 예제는 부속 노드 representation들의 dot product로 점수를 계산하는 방법을 사용한다.
|
|
|
|
.. code:: python
|
|
|
|
class ScorePredictor(nn.Module):
|
|
def forward(self, edge_subgraph, x):
|
|
with edge_subgraph.local_scope():
|
|
edge_subgraph.ndata['x'] = x
|
|
edge_subgraph.apply_edges(dgl.function.u_dot_v('x', 'x', 'score'))
|
|
return edge_subgraph.edata['score']
|
|
|
|
Negative 샘플러가 지정되면, DGL의 데이터 로더는 미니배치 마다 다음 3가지 아이템들을 만들어낸다.
|
|
|
|
- 샘플된 미니배치에 있는 모든 에지를 포함한 postive 그래프
|
|
- Negative 샘플러가 생성한 존재하지 않는 에지 모두를 포함한 negative 그래프
|
|
- 이웃 샘플러가 생성한 *message flow graph* (MFG)들의 리스트
|
|
|
|
이제 3가지 아이템와 입력 피쳐들을 받는 링크 예측 모델을 다음과 같이 정의할 수 있다.
|
|
|
|
.. code:: python
|
|
|
|
class Model(nn.Module):
|
|
def __init__(self, in_features, hidden_features, out_features):
|
|
super().__init__()
|
|
self.gcn = StochasticTwoLayerGCN(
|
|
in_features, hidden_features, out_features)
|
|
|
|
def forward(self, positive_graph, negative_graph, blocks, x):
|
|
x = self.gcn(blocks, x)
|
|
pos_score = self.predictor(positive_graph, x)
|
|
neg_score = self.predictor(negative_graph, x)
|
|
return pos_score, neg_score
|
|
|
|
학습 룹
|
|
~~~~~
|
|
|
|
학습 룹은 데이터 로더를 iterate하고, 그래프들과 입력 피쳐들을 위해서 정의한 모델에 입력하는 것일 뿐이다.
|
|
|
|
.. code:: python
|
|
|
|
def compute_loss(pos_score, neg_score):
|
|
# an example hinge loss
|
|
n = pos_score.shape[0]
|
|
return (neg_score.view(n, -1) - pos_score.view(n, -1) + 1).clamp(min=0).mean()
|
|
|
|
model = Model(in_features, hidden_features, out_features)
|
|
model = model.cuda()
|
|
opt = torch.optim.Adam(model.parameters())
|
|
|
|
for input_nodes, positive_graph, negative_graph, blocks in dataloader:
|
|
blocks = [b.to(torch.device('cuda')) for b in blocks]
|
|
positive_graph = positive_graph.to(torch.device('cuda'))
|
|
negative_graph = negative_graph.to(torch.device('cuda'))
|
|
input_features = blocks[0].srcdata['features']
|
|
pos_score, neg_score = model(positive_graph, negative_graph, blocks, input_features)
|
|
loss = compute_loss(pos_score, neg_score)
|
|
opt.zero_grad()
|
|
loss.backward()
|
|
opt.step()
|
|
|
|
DGL에서는 homogeneous 그래프들에 대한 링크 예측의 예제로 `unsupervised learning GraphSAGE <https://github.com/dmlc/dgl/blob/master/examples/pytorch/graphsage/train_sampling_unsupervised.py>`__ 를 제공한다.
|
|
|
|
Heterogeneous 그래프의 경우
|
|
~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
Heterogeneous 그래프들의 노드 representation들을 계산하는 모델은 에지 분류/리그레션을 위한 부속 노드
|
|
representation들을 구하는데 사용될 수 있다.
|
|
|
|
.. code:: python
|
|
|
|
class StochasticTwoLayerRGCN(nn.Module):
|
|
def __init__(self, in_feat, hidden_feat, out_feat, rel_names):
|
|
super().__init__()
|
|
self.conv1 = dglnn.HeteroGraphConv({
|
|
rel : dglnn.GraphConv(in_feat, hidden_feat, norm='right')
|
|
for rel in rel_names
|
|
})
|
|
self.conv2 = dglnn.HeteroGraphConv({
|
|
rel : dglnn.GraphConv(hidden_feat, out_feat, norm='right')
|
|
for rel in rel_names
|
|
})
|
|
|
|
def forward(self, blocks, x):
|
|
x = self.conv1(blocks[0], x)
|
|
x = self.conv2(blocks[1], x)
|
|
return x
|
|
|
|
점수를 예측하기 위한 homogeneous 그래프와 heterogeneous 그래프간의 유일한 구현상의 차이점은
|
|
:meth:`dgl.DGLGraph.apply_edges` 를 호출할 때 에지 타입들을 사용한다는 점이다.
|
|
|
|
.. code:: python
|
|
|
|
class ScorePredictor(nn.Module):
|
|
def forward(self, edge_subgraph, x):
|
|
with edge_subgraph.local_scope():
|
|
edge_subgraph.ndata['x'] = x
|
|
for etype in edge_subgraph.canonical_etypes:
|
|
edge_subgraph.apply_edges(
|
|
dgl.function.u_dot_v('x', 'x', 'score'), etype=etype)
|
|
return edge_subgraph.edata['score']
|
|
|
|
class Model(nn.Module):
|
|
def __init__(self, in_features, hidden_features, out_features, num_classes,
|
|
etypes):
|
|
super().__init__()
|
|
self.rgcn = StochasticTwoLayerRGCN(
|
|
in_features, hidden_features, out_features, etypes)
|
|
self.pred = ScorePredictor()
|
|
|
|
def forward(self, positive_graph, negative_graph, blocks, x):
|
|
x = self.rgcn(blocks, x)
|
|
pos_score = self.pred(positive_graph, x)
|
|
neg_score = self.pred(negative_graph, x)
|
|
return pos_score, neg_score
|
|
|
|
데이터 로더 구현도 노드 분류을 위한 것과 아주 비슷하다. 유일한 차이점은 negative 샘플러를 사용하며, 노드 타입과 노드 ID 텐서들의 사전 대신에 에지 타입과 에지 ID 텐서들의 사전을 사용한다는 것이다.
|
|
|
|
.. code:: python
|
|
|
|
sampler = dgl.dataloading.MultiLayerFullNeighborSampler(2)
|
|
dataloader = dgl.dataloading.EdgeDataLoader(
|
|
g, train_eid_dict, sampler,
|
|
negative_sampler=dgl.dataloading.negative_sampler.Uniform(5),
|
|
batch_size=1024,
|
|
shuffle=True,
|
|
drop_last=False,
|
|
num_workers=4)
|
|
|
|
만약 직접 만든 negative 샘플링 함수를 사용하기를 원한다면, 그 함수는 원본 그래프, 에지 타입과 에지 ID 텐서들의 dictionary를 인자로 받아야하고, 에지 타입들과 소스-목적지 배열 쌍의 dictionary를 리턴해야한다. 다음은 예제 함수이다.
|
|
|
|
.. code:: python
|
|
|
|
class NegativeSampler(object):
|
|
def __init__(self, g, k):
|
|
# caches the probability distribution
|
|
self.weights = {
|
|
etype: g.in_degrees(etype=etype).float() ** 0.75
|
|
for etype in g.canonical_etypes}
|
|
self.k = k
|
|
|
|
def __call__(self, g, eids_dict):
|
|
result_dict = {}
|
|
for etype, eids in eids_dict.items():
|
|
src, _ = g.find_edges(eids, etype=etype)
|
|
src = src.repeat_interleave(self.k)
|
|
dst = self.weights[etype].multinomial(len(src), replacement=True)
|
|
result_dict[etype] = (src, dst)
|
|
return result_dict
|
|
|
|
다음으로는 에지 타입들와 에지 ID들의 dictionary와 negative 샘플러를 데이터 로더에 전달한다. 예를 들면, 아래 코드는 heterogeneous 그래프의 모든 에지들을 iterate하는 예이다.
|
|
|
|
.. code:: python
|
|
|
|
train_eid_dict = {
|
|
etype: g.edges(etype=etype, form='eid')
|
|
for etype in g.canonical_etypes}
|
|
|
|
dataloader = dgl.dataloading.EdgeDataLoader(
|
|
g, train_eid_dict, sampler,
|
|
negative_sampler=NegativeSampler(g, 5),
|
|
batch_size=1024,
|
|
shuffle=True,
|
|
drop_last=False,
|
|
num_workers=4)
|
|
|
|
학습 룹은 ``compute_loss`` 의 구현이 노드 타입들과 예측 값에 대한 두 사전들을 인자로 받는다는 점을 제외하면, homogeneous 그래프의 학습 룹 구현과 거의 같다.
|
|
|
|
.. code:: python
|
|
|
|
model = Model(in_features, hidden_features, out_features, num_classes, etypes)
|
|
model = model.cuda()
|
|
opt = torch.optim.Adam(model.parameters())
|
|
|
|
for input_nodes, positive_graph, negative_graph, blocks in dataloader:
|
|
blocks = [b.to(torch.device('cuda')) for b in blocks]
|
|
positive_graph = positive_graph.to(torch.device('cuda'))
|
|
negative_graph = negative_graph.to(torch.device('cuda'))
|
|
input_features = blocks[0].srcdata['features']
|
|
pos_score, neg_score = model(positive_graph, negative_graph, blocks, input_features)
|
|
loss = compute_loss(pos_score, neg_score)
|
|
opt.zero_grad()
|
|
loss.backward()
|
|
opt.step()
|
|
|
|
|
|
|