pyg-nightly 2.7.0.dev20250212__py3-none-any.whl → 2.7.0.dev20250213__py3-none-any.whl

{pyg_nightly-2.7.0.dev20250212.dist-info → pyg_nightly-2.7.0.dev20250213.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: pyg-nightly
-Version: 2.7.0.dev20250212
+Version: 2.7.0.dev20250213
 Summary: Graph Neural Network Library for PyTorch
 Keywords: deep-learning,pytorch,geometric-deep-learning,graph-neural-networks,graph-convolutional-networks
 Author-email: Matthias Fey <matthias@pyg.org>

{pyg_nightly-2.7.0.dev20250212.dist-info → pyg_nightly-2.7.0.dev20250213.dist-info}/RECORD

@@ -1,4 +1,4 @@
-torch_geometric/__init__.py,sha256=hKo_s3A34_-rUX4Hzm8jMIHesXZ_6czNizE8bAkdnNc,1904
+torch_geometric/__init__.py,sha256=wOLNLy1SUhTvDg4h0bCQM5edX6RXk83qnn4omNGqmaw,1904
 torch_geometric/_compile.py,sha256=f-WQeH4VLi5Hn9lrgztFUCSrN_FImjhQa6BxFzcYC38,1338
 torch_geometric/_onnx.py,sha256=V9ffrIKSqhDw6xUZ12lkuSfNs48cQp2EeJ6Z19GfnVw,349
 torch_geometric/backend.py,sha256=lVaf7aLoVaB3M-UcByUJ1G4T4FOK6LXAg0CF4W3E8jo,1575
@@ -288,8 +288,8 @@ torch_geometric/loader/shadow.py,sha256=_hCspYf9SlJYX0lqEjxFec9e9t1iMScNThOoWR1w
 torch_geometric/loader/temporal_dataloader.py,sha256=AQ2QFeiXKbPp6I8sUeE8H7br-1_yndivXt7Z6_w62zI,2248
 torch_geometric/loader/utils.py,sha256=f27mczQ7fEP2HpTsJGJxKS0slPu0j8zTba3jP8ViNck,14901
 torch_geometric/loader/zip_loader.py,sha256=3lt10fD15Rxm1WhWzypswGzCEwUz4h8OLCD1nE15yNg,3843
-torch_geometric/metrics/__init__.py,sha256=bkNC9USDDxPq9-_duiKTXJoDv1Sb0-zrpqTeOGv55CM,635
-torch_geometric/metrics/link_pred.py,sha256=VEpa5605jJ5uH1G-SaxQNKelTpU156VsZMmde-Z22e4,27951
+torch_geometric/metrics/__init__.py,sha256=3krvDobW6vV5yHTjq2S2pmOXxNfysNG26muq7z48e94,699
+torch_geometric/metrics/link_pred.py,sha256=X8LXJvJ0dwjOeO0PvB6xe-qkBntmefHKC4zex7Q2i0I,29766
 torch_geometric/nn/__init__.py,sha256=RrWRzEoqtR3lsO2lAzYXboLPb3uYEX2z3tLxiBIVWjc,847
 torch_geometric/nn/data_parallel.py,sha256=lDAxRi83UNuzAQSj3eu9K2sQheOIU6wqR5elS6oDs90,4764
 torch_geometric/nn/encoding.py,sha256=QNjwWczYExZ1wRGBmpuqYbn6tB7NC4BU-DEgzjhcZqw,3115
@@ -630,6 +630,6 @@ torch_geometric/utils/undirected.py,sha256=H_nfpI0_WluOG6VfjPyldvcjL4w5USAKWu2x5
 torch_geometric/visualization/__init__.py,sha256=PyR_4K5SafsJrBr6qWrkjKr6GBL1b7FtZybyXCDEVwY,154
 torch_geometric/visualization/graph.py,sha256=ZuLPL92yGRi7lxlqsUPwL_EVVXF7P2kMcveTtW79vpA,4784
 torch_geometric/visualization/influence.py,sha256=CWMvuNA_Nf1sfbJmQgn58yS4OFpeKXeZPe7kEuvkUBw,477
-pyg_nightly-2.7.0.dev20250212.dist-info/WHEEL,sha256=CpUCUxeHQbRN5UGRQHYRJorO5Af-Qy_fHMctcQ8DSGI,82
-pyg_nightly-2.7.0.dev20250212.dist-info/METADATA,sha256=imhjF5_GnKoAZ1c2oZk1Q1MFm-5fj30dvj8iYmb-1kg,62977
-pyg_nightly-2.7.0.dev20250212.dist-info/RECORD,,
+pyg_nightly-2.7.0.dev20250213.dist-info/WHEEL,sha256=CpUCUxeHQbRN5UGRQHYRJorO5Af-Qy_fHMctcQ8DSGI,82
+pyg_nightly-2.7.0.dev20250213.dist-info/METADATA,sha256=KMYn4w4Bn5To5C_3fCsn61FLL62Iz10xQk493Q4OeCE,62977
+pyg_nightly-2.7.0.dev20250213.dist-info/RECORD,,

torch_geometric/__init__.py

@@ -30,7 +30,7 @@ from .lazy_loader import LazyLoader
 contrib = LazyLoader('contrib', globals(), 'torch_geometric.contrib')
 graphgym = LazyLoader('graphgym', globals(), 'torch_geometric.graphgym')
 
-__version__ = '2.7.0.dev20250212'
+__version__ = '2.7.0.dev20250213'
 
 __all__ = [
     'Index',

torch_geometric/metrics/__init__.py

@@ -13,6 +13,7 @@ from .link_pred import (
     LinkPredCoverage,
     LinkPredDiversity,
     LinkPredPersonalization,
+    LinkPredAveragePopularity,
 )
 
 link_pred_metrics = [
@@ -28,6 +29,7 @@ link_pred_metrics = [
     'LinkPredCoverage',
     'LinkPredDiversity',
     'LinkPredPersonalization',
+    'LinkPredAveragePopularity',
 ]
 
 __all__ = link_pred_metrics

torch_geometric/metrics/link_pred.py

@@ -722,12 +722,14 @@ class LinkPredPersonalization(_LinkPredMetric):
             of user recommendations should be processed at once.
             (default: :obj:`2**16`)
     """
+    higher_is_better: bool = True
+
     def __init__(self, k: int, batch_size: int = 2**16) -> None:
         super().__init__(k)
         self.batch_size = batch_size
 
         if WITH_TORCHMETRICS:
-            self.add_state("preds", default=[], dist_reduce_fx="cat")
+            self.add_state('preds', default=[], dist_reduce_fx='cat')
             self.add_state('dev_tensor', torch.empty(0), dist_reduce_fx='sum')
         else:
             self.preds: List[Tensor] = []
@@ -787,3 +789,51 @@ class LinkPredPersonalization(_LinkPredMetric):
 
     def _reset(self) -> None:
         self.preds = []
+
+
+class LinkPredAveragePopularity(_LinkPredMetric):
+    r"""A link prediction metric to compute the Average Recommendation
+    Popularity (ARP) @ :math:`k`, which provides insights into the model's
+    tendency to recommend popular items by averaging the popularity scores of
+    items within the top-:math:`k` recommendations.
+
+    Args:
+        k (int): The number of top-:math:`k` predictions to evaluate against.
+        popularity (torch.Tensor): The popularity of every item in the training
+            set, *e.g.*, the number of times an item has been rated.
+    """
+    higher_is_better: bool = False
+
+    def __init__(self, k: int, popularity: Tensor) -> None:
+        super().__init__(k)
+
+        if WITH_TORCHMETRICS:
+            self.add_state('accum', torch.tensor(0.), dist_reduce_fx='sum')
+            self.add_state('total', torch.tensor(0), dist_reduce_fx='sum')
+        else:
+            self.register_buffer('accum', torch.tensor(0.))
+            self.register_buffer('total', torch.tensor(0))
+
+        self.popularity: Tensor
+        self.register_buffer('popularity', popularity)
+
+    def update(
+        self,
+        pred_index_mat: Tensor,
+        edge_label_index: Union[Tensor, Tuple[Tensor, Tensor]],
+        edge_label_weight: Optional[Tensor] = None,
+    ) -> None:
+        pred_index_mat = pred_index_mat[:, :self.k]
+        popularity = self.popularity[pred_index_mat]
+        popularity = popularity.to(self.accum.dtype).mean(dim=-1)
+        self.accum += popularity.sum()
+        self.total += popularity.numel()
+
+    def compute(self) -> Tensor:
+        if self.total == 0:
+            return torch.zeros_like(self.accum)
+        return self.accum / self.total
+
+    def _reset(self) -> None:
+        self.accum.zero_()
+        self.total.zero_()