Skip to content

GitLab

"vscode:/vscode.git/clone" did not exist on "7f7e7663e1bd5b8ae4e6f4a0b561319777769bdf"
Unverified Commit 598f3f36 authored by yxy235's avatar yxy235 Committed by GitHub
Browse files

Revert "[GraphBolt] Add NOT deduplication func to homo graph." (#6489) 


Co-authored-by: default avatarHongzhi (Steve), Chen <chenhongzhi.nkcs@gmail.com>
parent 1b5b7de5
Show whitespace changes
Inline Side-by-side
Showing with 16 additions and 110 deletions
python/dgl/graphbolt/impl/csc_sampling_graph.py
View file @ 598f3f36
......@@ -308,13 +308,12 @@ class CSCSamplingGraph(SamplingGraph):
# TODO: change the result to 'SampledSubgraphImpl'.
return self._c_csc_graph.in_subgraph(nodes)
def _convert_to_sampled_subgraph_node_pairs_and_eids(
def _convert_to_sampled_subgraph(
self,
C_sampled_subgraph: torch.ScriptObject,
):
"""An internal function used to generate node pairs and eids of
structure `SampledSubgraphImpl` from a fused homogeneous sampled
subgraph."""
"""An internal function used to convert a fused homogeneous sampled
subgraph to general struct 'SampledSubgraphImpl'."""
column_num = (
C_sampled_subgraph.indptr[1:] - C_sampled_subgraph.indptr[:-1]
)
......@@ -358,48 +357,6 @@ class CSCSamplingGraph(SamplingGraph):
node_pairs=node_pairs, original_edge_ids=original_edge_ids
)
def _convert_to_sampled_subgraph(
self,
C_sampled_subgraph: torch.ScriptObject,
):
"""An internal function used to convert a fused homogeneous sampled
subgraph to general struct 'SampledSubgraphImpl'."""
type_per_edge = C_sampled_subgraph.type_per_edge
if type_per_edge is None:
column_num = (
C_sampled_subgraph.indptr[1:] - C_sampled_subgraph.indptr[:-1]
)
column = torch.arange(len(column_num)).repeat_interleave(column_num)
row = torch.arange(len(C_sampled_subgraph.indices)) + len(
column_num
)
original_edge_ids = C_sampled_subgraph.original_edge_ids
has_original_eids = (
self.edge_attributes is not None
and ORIGINAL_EDGE_ID in self.edge_attributes
)
if has_original_eids and original_edge_ids is not None:
original_edge_ids = self.edge_attributes[ORIGINAL_EDGE_ID][
original_edge_ids
]
# The sampled graph is already a homogeneous graph.
node_pairs = (row, column)
return SampledSubgraphImpl(
node_pairs=node_pairs,
original_edge_ids=original_edge_ids,
original_column_node_ids=(
C_sampled_subgraph.original_column_node_ids
),
original_row_node_ids=torch.cat(
(
C_sampled_subgraph.original_column_node_ids,
C_sampled_subgraph.indices,
)
),
)
else:
raise RuntimeError("Not implemented yet.")
def _convert_to_homogeneous_nodes(self, nodes):
homogeneous_nodes = []
for ntype, ids in nodes.items():
......@@ -413,7 +370,6 @@ class CSCSamplingGraph(SamplingGraph):
fanouts: torch.Tensor,
replace: bool = False,
probs_name: Optional[str] = None,
deduplicate=True,
) -> SampledSubgraphImpl:
"""Sample neighboring edges of the given nodes and return the induced
subgraph.
......@@ -453,10 +409,6 @@ class CSCSamplingGraph(SamplingGraph):
corresponding to each neighboring edge of a node. It must be a 1D
floating-point or boolean tensor, with the number of elements
equalling the total number of edges.
deduplicate: bool
Boolean indicating whether seeds between hops will be deduplicated.
If True, the same elements in seeds will be removed to only one.
Otherwise, the same elements will be remained.
Returns
-------
SampledSubgraphImpl
......@@ -488,11 +440,7 @@ class CSCSamplingGraph(SamplingGraph):
C_sampled_subgraph = self._sample_neighbors(
nodes, fanouts, replace, probs_name
)
if deduplicate:
return self._convert_to_sampled_subgraph_node_pairs_and_eids(
C_sampled_subgraph
)
else:
return self._convert_to_sampled_subgraph(C_sampled_subgraph)
def _check_sampler_arguments(self, nodes, fanouts, probs_name):
......@@ -600,7 +548,6 @@ class CSCSamplingGraph(SamplingGraph):
fanouts: torch.Tensor,
replace: bool = False,
probs_name: Optional[str] = None,
deduplicate=True,
) -> SampledSubgraphImpl:
"""Sample neighboring edges of the given nodes and return the induced
subgraph via layer-neighbor sampling from the NeurIPS 2023 paper
......@@ -642,10 +589,6 @@ class CSCSamplingGraph(SamplingGraph):
corresponding to each neighboring edge of a node. It must be a 1D
floating-point or boolean tensor, with the number of elements
equalling the total number of edges.
deduplicate: bool
Boolean indicating whether seeds between hops will be deduplicated.
If True, the same elements in seeds will be deleted to only one.
Otherwise, the same elements will be remained.
Returns
-------
SampledSubgraphImpl
......@@ -687,11 +630,7 @@ class CSCSamplingGraph(SamplingGraph):
has_original_eids,
probs_name,
)
if deduplicate:
return self._convert_to_sampled_subgraph_node_pairs_and_eids(
C_sampled_subgraph
)
else:
return self._convert_to_sampled_subgraph(C_sampled_subgraph)
def sample_negative_edges_uniform(
......
python/dgl/graphbolt/impl/neighbor_sampler.py
View file @ 598f3f36
......@@ -116,13 +116,14 @@ class NeighborSampler(SubgraphSampler):
self.fanouts[hop],
self.replace,
self.prob_name,
self.deduplicate,
)
if self.deduplicate:
(
original_row_node_ids,
compacted_node_pairs,
) = unique_and_compact_node_pairs(subgraph.node_pairs, seeds)
else:
raise RuntimeError("Not implemented yet.")
subgraph = SampledSubgraphImpl(
node_pairs=compacted_node_pairs,
original_column_node_ids=seeds,
......@@ -130,7 +131,7 @@ class NeighborSampler(SubgraphSampler):
original_edge_ids=subgraph.original_edge_ids,
)
subgraphs.insert(0, subgraph)
seeds = subgraph.original_row_node_ids
seeds = original_row_node_ids
return seeds, subgraphs
......
tests/python/pytorch/graphbolt/test_subgraph_sampler.py
View file @ 598f3f36
import dgl
import dgl.graphbolt as gb
import gb_test_utils
import pytest
......@@ -193,36 +192,3 @@ def test_SubgraphSampler_Link_Hetero_With_Negative(labor):
Sampler = gb.LayerNeighborSampler if labor else gb.NeighborSampler
neighbor_dp = Sampler(negative_dp, graph, fanouts)
assert len(list(neighbor_dp)) == 5
@pytest.mark.parametrize("labor", [False, True])
def test_test_SubgraphSampler_without_dedpulication(labor):
graph = dgl.graph(
([5, 0, 1, 5, 6, 7, 2, 2, 4], [0, 1, 2, 2, 2, 2, 3, 4, 4])
)
graph = gb.from_dglgraph(graph, True)
seed_nodes = torch.LongTensor([0, 3, 4])
itemset = gb.ItemSet(seed_nodes, names="seed_nodes")
item_sampler = gb.ItemSampler(itemset, batch_size=len(seed_nodes))
num_layer = 2
fanouts = [torch.LongTensor([2]) for _ in range(num_layer)]
Sampler = gb.LayerNeighborSampler if labor else gb.NeighborSampler
datapipe = Sampler(item_sampler, graph, fanouts, deduplicate=False)
length = [17, 7]
compacted_dst = [
torch.tensor([0, 1, 2, 2, 4, 4, 5, 5, 6, 6]),
torch.tensor([0, 1, 2, 2]),
]
seeds = [torch.tensor([0, 3, 4, 5, 2, 2, 4]), torch.tensor([0, 3, 4])]
for data in datapipe:
for step, sampled_subgraph in enumerate(data.sampled_subgraphs):
assert len(sampled_subgraph.original_row_node_ids) == length[step]
assert torch.equal(
sampled_subgraph.node_pairs[1], compacted_dst[step]
)
assert torch.equal(
sampled_subgraph.original_column_node_ids, seeds[step]
)
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment