pyg-nightly 2.7.0.dev20251008__py3-none-any.whl → 2.8.0.dev20251124__py3-none-any.whl

{pyg_nightly-2.7.0.dev20251008.dist-info → pyg_nightly-2.8.0.dev20251124.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pyg-nightly
-Version: 2.7.0.dev20251008
+Version: 2.8.0.dev20251124
 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.dev20251008.dist-info → pyg_nightly-2.8.0.dev20251124.dist-info}/RECORD

@@ -1,4 +1,4 @@
-torch_geometric/__init__.py,sha256=uBfYWACp7LGhh_ksb2Aqr0daci4EfYWlgcN_kwYn29M,2292
+torch_geometric/__init__.py,sha256=aY1pU-eCTEljl3jizH5K9dsuVlUbq4mmUeavVQrulRw,2292
 torch_geometric/_compile.py,sha256=9yqMTBKatZPr40WavJz9FjNi7pQj8YZAZOyZmmRGXgc,1351
 torch_geometric/_onnx.py,sha256=ODB_8cwFUiwBUjngXn6-K5HHb7IDul7DDXuuGX7vj_0,8178
 torch_geometric/backend.py,sha256=lVaf7aLoVaB3M-UcByUJ1G4T4FOK6LXAg0CF4W3E8jo,1575
@@ -151,7 +151,7 @@ torch_geometric/datasets/shapenet.py,sha256=tn3HiQQAr6lxHrqxfOVaAtl40guwFYTXWCbS
 torch_geometric/datasets/shrec2016.py,sha256=cTLhctbqE0EUEvKddJFhPzDb1oLKXOth4O_WzsWtyMk,6323
 torch_geometric/datasets/snap_dataset.py,sha256=deJvB6cpIQ3bu_pcWoqgEo1-Kl_NcFi7ZSUci645X0U,9481
 torch_geometric/datasets/suite_sparse.py,sha256=eqjH4vAUq872qdk3YdLkZSwlu6r7HHpTgK0vEVGmY1s,3278
-torch_geometric/datasets/tag_dataset.py,sha256=jslijGCh37ip2YkrQLyvbk-1QRJ3yqFpmzuQSxckXrE,19402
+torch_geometric/datasets/tag_dataset.py,sha256=TwZMDxnFGjl4vPosZIp1mmqMXjxcMt3WcgeiTeKMjuU,19788
 torch_geometric/datasets/taobao.py,sha256=CUcZpbWsNTasevflO8zqP0YvENy89P7wpKS4MHaDJ6Q,4170
 torch_geometric/datasets/teeth3ds.py,sha256=hZvhcq9lsQENNFr5hk50w2T3CgxE_tlnQfrCgN6uIDQ,9919
 torch_geometric/datasets/tosca.py,sha256=nUSF8NQT1GlkwWQLshjWmr8xORsvRHzzIqhUyDCvABc,4632
@@ -278,14 +278,14 @@ torch_geometric/llm/models/llm.py,sha256=039mq9rZBZMyZW5rYj0fMP5kl9RJAI7N-oJyC4M
 torch_geometric/llm/models/llm_judge.py,sha256=qhc8hmIPNhcfLVRyBVk7jQW7ncoIb9QYw7rcsGAIpyg,6457
 torch_geometric/llm/models/molecule_gpt.py,sha256=RWoP4RMsoRzZtuedPCLNCfooqibCqxkuAhH-pyek9No,7641
 torch_geometric/llm/models/protein_mpnn.py,sha256=SwTgafSbI2KJ-yqzn0trZtVWLmfo0_kPEaWSNJUCt70,12266
-torch_geometric/llm/models/sentence_transformer.py,sha256=TSXBxeTktj10YU-h_1prdMCCmAG8MTOKMm760ch4g30,6377
+torch_geometric/llm/models/sentence_transformer.py,sha256=XYDN7xYyMqUNZyxpY6EjDjfYt1mope5iGsBZ2fLc1J8,7041
 torch_geometric/llm/models/txt2kg.py,sha256=CjWXCa_WrqIlBfOSPMAK-mnaX19dvH_YhXMWSuLkk4o,14074
 torch_geometric/llm/models/vision_transformer.py,sha256=aPuVfpSwGR96KaicRYut49g6ShrCklbouaLwyPuwhBQ,1022
 torch_geometric/llm/utils/__init__.py,sha256=P5By_n15MqkUU1tfh87PGE--J7RVygPeDSBOTy_VlZ0,292
-torch_geometric/llm/utils/backend_utils.py,sha256=AcvZ8ym3UKCWwWoMl8sNRnj4FSl0_srHw9yxZAKiyeU,15840
+torch_geometric/llm/utils/backend_utils.py,sha256=vde10npVYZTY6ONExu-eeMgzouMnhdFcoTe8GyYuL1k,15874
 torch_geometric/llm/utils/feature_store.py,sha256=d60n3TlclEhlqoDEHKmvvGI6t8r0nur1BNwXyqqtj24,5903
 torch_geometric/llm/utils/graph_store.py,sha256=_Hh0aGnokUn0zvOC80xUfT4TtX_7G4KIDoEBkNXkgHY,7103
-torch_geometric/llm/utils/vectorrag.py,sha256=m51drMNXsGQTN6qkbR8QiHb8jvcrBlZDHzEjsEmtnes,4753
+torch_geometric/llm/utils/vectorrag.py,sha256=7WE73NOzHfChSvmYEfg2dHp8JIgLtX4XaKVRrsKmkc0,4791
 torch_geometric/loader/__init__.py,sha256=w9LSTbyrLRkyrLXi_10d80csWgfKOKDRQDJXRdcfD0M,1835
 torch_geometric/loader/base.py,sha256=ataIwNEYL0px3CN3LJEgXIVTRylDHB6-yBFXXuX2JN0,1615
 torch_geometric/loader/cache.py,sha256=S65heO3YTyUPbttqizCNtKPHIoAw5iHRpbvw6KlXmok,2106
@@ -319,7 +319,7 @@ torch_geometric/nn/fx.py,sha256=PDtaHJAgodh4xf8FNl4fVxPGZJDbRaq3Q9z8qb1DNNI,1606
 torch_geometric/nn/glob.py,sha256=MdHjcUlHmFmTevzwND1_x7dXXJPzIDTBJRGOrGdZ8dQ,1088
 torch_geometric/nn/inits.py,sha256=_8FqacCLPz5Ft2zB5s6dtKGTKWtfrLyCLLuv1QvyKjk,2457
 torch_geometric/nn/lr_scheduler.py,sha256=_FWdIgGPDSZCK1TZFWHSP5RfpY83Kyhlz7Ja6YHPQVo,8937
-torch_geometric/nn/model_hub.py,sha256=2x8uN80BwW2pdBGtU4LNF-8pUtGZMxr0btQCVSgeKwA,9550
+torch_geometric/nn/model_hub.py,sha256=GxgKE9P7wwEHp7dG_pnLI562WGHXIuHkOWD3kUzkX-g,8827
 torch_geometric/nn/module_dict.py,sha256=c6ThkEfju01ZyhERA8rZgr9oawVfwqOBMrdG3bzSsro,2377
 torch_geometric/nn/parameter_dict.py,sha256=RJnid_I8jXTjIoDKVr0Ej2E2XKOLxH_lXxLeEHB_wUg,2412
 torch_geometric/nn/reshape.py,sha256=WJvc_oPPcfsFqN97i4oJRMor17ar5IPeIu8BevKIyIk,426
@@ -424,9 +424,9 @@ torch_geometric/nn/conv/wl_conv_continuous.py,sha256=nnfd5JVAR2UYz6AQxwCN2a8C6RX
 torch_geometric/nn/conv/x_conv.py,sha256=c_qnD-o9-qMa-vaOgEDGb5ZT1NdhS2vrhTQdp-8cYIo,6013
 torch_geometric/nn/conv/cugraph/__init__.py,sha256=Z1neZpdSe95MyMB9Zt_ll2mj4ogEecQpkSxS0rq63x4,251
 torch_geometric/nn/conv/cugraph/base.py,sha256=zt0vbZ6ANqbVjgWNxcLfQSlSVDOn1qK7wzeZ2uB2sMk,6351
-torch_geometric/nn/conv/cugraph/gat_conv.py,sha256=JZ2v6ZLA3VRL7s3Bk0QB1N2g6CV2tBtu6Z3Pwj9uja4,2874
-torch_geometric/nn/conv/cugraph/rgcn_conv.py,sha256=Dm-tUBKb0-ewBUyYyr4bB69N5cmHQZjEpFcVkzLWB8k,4002
-torch_geometric/nn/conv/cugraph/sage_conv.py,sha256=oTmtCjeFbRMUxFgyXhpPNMBlG96cF6voA27jUpvzfFk,2830
+torch_geometric/nn/conv/cugraph/gat_conv.py,sha256=f78t9i_4BHkRDrnZtXiaDCUrnFYX07EuehZvLdZg2rY,3160
+torch_geometric/nn/conv/cugraph/rgcn_conv.py,sha256=2vqNiw9GyRktn42JVj_oco0frgTGfEZltCz1sg9f3eE,4161
+torch_geometric/nn/conv/cugraph/sage_conv.py,sha256=2W2CtyvSBNztpLjLhsU8DnPyXxwfMZJlGktADHphskw,2989
 torch_geometric/nn/conv/utils/__init__.py,sha256=VWVDyQQu2mP-O3lzP-TEJUSeyhLizTiAb5rMLsUrUzA,852
 torch_geometric/nn/conv/utils/cheatsheet.py,sha256=-AzSVc5icHfWIw9UxYX8ea_1dziC4v4st_KDwwUeV1A,2792
 torch_geometric/nn/dense/__init__.py,sha256=_t9aKRZmNqRPneW9edJ4Hh7hGHU9DaPpqf9g55GQJsk,847
@@ -499,7 +499,7 @@ torch_geometric/nn/pool/__init__.py,sha256=VU9cPdLC-MPgt1kfS0ZwehfSD3g0V30VQuR1W
 torch_geometric/nn/pool/approx_knn.py,sha256=n7C8Cbar6o5tJcuAbzhM5hqMK26hW8dm5DopuocidO0,3967
 torch_geometric/nn/pool/asap.py,sha256=p8fwpMOeCUyJrdvMmLoTMzr0tI9YCTnefMx8ylIv5xE,6683
 torch_geometric/nn/pool/avg_pool.py,sha256=pwiQh14BCVsT-iULqVAFW-Dxt7DjFOu8CQX_Hu34vZc,3966
-torch_geometric/nn/pool/cluster_pool.py,sha256=XSwZa9wvbJppvCqHAhGky0MzQwNkXNVcnIKdI6ZYuwM,5225
+torch_geometric/nn/pool/cluster_pool.py,sha256=57UNpThRvLumY0159T8nBhxXvZE0mT5YMoCyrpoRmtk,5247
 torch_geometric/nn/pool/consecutive.py,sha256=7dMiMd5IybNeml1RqZq436FI6sod5ZUxTuDWJjr5syo,273
 torch_geometric/nn/pool/decimation.py,sha256=AjbU2h_Gl_EQcfkhF977EnrLJ2kait_e4HyCNKRyxPw,1601
 torch_geometric/nn/pool/edge_pool.py,sha256=cXgcN5xF8z5NeycYMX9m1zoAk1jtSdyK42YiNNHTeow,8571
@@ -654,7 +654,7 @@ torch_geometric/utils/undirected.py,sha256=H_nfpI0_WluOG6VfjPyldvcjL4w5USAKWu2x5
 torch_geometric/visualization/__init__.py,sha256=b-HnVesXjyJ_L1N-DnjiRiRVf7lhwKaBQF_2i5YMVSU,208
 torch_geometric/visualization/graph.py,sha256=mfZHXYfiU-CWMtfawYc80IxVwVmtK9hbIkSKhM_j7oI,14311
 torch_geometric/visualization/influence.py,sha256=CWMvuNA_Nf1sfbJmQgn58yS4OFpeKXeZPe7kEuvkUBw,477
-pyg_nightly-2.7.0.dev20251008.dist-info/licenses/LICENSE,sha256=ic-27cMJc1kWoMEYncz3Ya3Ur2Bi3bNLWib2DT763-o,1067
-pyg_nightly-2.7.0.dev20251008.dist-info/WHEEL,sha256=G2gURzTEtmeR8nrdXUJfNiB3VYVxigPQ-bEQujpNiNs,82
-pyg_nightly-2.7.0.dev20251008.dist-info/METADATA,sha256=sJdSN3mBDJnXEUNKpITdTXObI5YAt9bps3o7xKEL00w,63680
-pyg_nightly-2.7.0.dev20251008.dist-info/RECORD,,
+pyg_nightly-2.8.0.dev20251124.dist-info/licenses/LICENSE,sha256=ic-27cMJc1kWoMEYncz3Ya3Ur2Bi3bNLWib2DT763-o,1067
+pyg_nightly-2.8.0.dev20251124.dist-info/WHEEL,sha256=G2gURzTEtmeR8nrdXUJfNiB3VYVxigPQ-bEQujpNiNs,82
+pyg_nightly-2.8.0.dev20251124.dist-info/METADATA,sha256=8O-Cslu9xIWBaT2C0oeVek100Acxa7FjCVFfT1IH3g0,63680
+pyg_nightly-2.8.0.dev20251124.dist-info/RECORD,,

torch_geometric/__init__.py

@@ -31,7 +31,7 @@ from .lazy_loader import LazyLoader
 contrib = LazyLoader('contrib', globals(), 'torch_geometric.contrib')
 graphgym = LazyLoader('graphgym', globals(), 'torch_geometric.graphgym')
 
-__version__ = '2.7.0.dev20251008'
+__version__ = '2.8.0.dev20251124'
 
 __all__ = [
     'Index',

torch_geometric/datasets/tag_dataset.py

@@ -137,10 +137,13 @@ class TAGDataset(InMemoryDataset):
         self.token_on_disk = token_on_disk
         self.tokenize_batch_size = tokenize_batch_size
         self._token = self.tokenize_graph(self.tokenize_batch_size)
-        self._llm_explanation_token = self.tokenize_graph(
-            self.tokenize_batch_size, text_type='llm_explanation')
-        self._all_token = self.tokenize_graph(self.tokenize_batch_size,
-                                              text_type='all')
+        self._llm_explanation_token: Dict[str, Tensor] = {}
+        self._all_token: Dict[str, Tensor] = {}
+        if self.name in self.llm_explanation_id:
+            self._llm_explanation_token = self.tokenize_graph(
+                self.tokenize_batch_size, text_type='llm_explanation')
+            self._all_token = self.tokenize_graph(self.tokenize_batch_size,
+                                                  text_type='all')
         self.__num_classes__ = dataset.num_classes
 
     @property
@@ -170,14 +173,16 @@ class TAGDataset(InMemoryDataset):
 
     @property
     def llm_explanation_token(self) -> Dict[str, Tensor]:
-        if self._llm_explanation_token is None:  # lazy load
+        if self._llm_explanation_token is None and \
+                self.name in self.llm_explanation_id:
             self._llm_explanation_token = self.tokenize_graph(
                 text_type='llm_explanation')
         return self._llm_explanation_token
 
     @property
     def all_token(self) -> Dict[str, Tensor]:
-        if self._all_token is None:  # lazy load
+        if self._all_token is None and \
+                self.name in self.llm_explanation_id:
             self._all_token = self.tokenize_graph(text_type='all')
         return self._all_token
 
@@ -230,13 +235,15 @@ class TAGDataset(InMemoryDataset):
                                             filename='node-text.csv.gz',
                                             log=True)
         self.text = list(read_csv(raw_text_path)['text'])
-        print('downloading llm explanations')
-        llm_explanation_path = download_google_url(
-            id=self.llm_explanation_id[self.name], folder=f'{self.root}/raw',
-            filename='node-gpt-response.csv.gz', log=True)
-        self.llm_explanation = list(read_csv(llm_explanation_path)['text'])
-        print('downloading llm predictions')
-        fs.cp(f'{self.llm_prediction_url}/{self.name}.csv', self.raw_dir)
+        if self.name in self.llm_explanation_id:
+            print('downloading llm explanations')
+            llm_explanation_path = download_google_url(
+                id=self.llm_explanation_id[self.name],
+                folder=f'{self.root}/raw', filename='node-gpt-response.csv.gz',
+                log=True)
+            self.llm_explanation = list(read_csv(llm_explanation_path)['text'])
+            print('downloading llm predictions')
+            fs.cp(f'{self.llm_prediction_url}/{self.name}.csv', self.raw_dir)
 
     def process(self) -> None:
         # process Title and Abstraction
@@ -276,6 +283,14 @@ class TAGDataset(InMemoryDataset):
             for i, pred in enumerate(preds):
                 pl[i][:len(pred)] = torch.tensor(
                     pred[:self.llm_prediction_topk], dtype=torch.long) + 1
+
+            if self.llm_explanation is None or pl is None:
+                raise ValueError(
+                    "The TAGDataset only have ogbn-arxiv LLM explanations"
+                    "and predictions in default. The llm explanation and"
+                    "prediction of each node is not specified.Please pass in"
+                    "'llm_explanation' and 'llm_prediction' when"
+                    "convert your dataset to Text Attribute Graph Dataset")
         elif self.name in self.llm_explanation_id:
             self.download()
         else:
@@ -283,13 +298,6 @@ class TAGDataset(InMemoryDataset):
                 'The dataset is not ogbn-arxiv,'
                 'please pass in your llm explanation list to `llm_explanation`'
                 'and llm prediction list to `llm_prediction`')
-        if self.llm_explanation is None or pl is None:
-            raise ValueError(
-                "The TAGDataset only have ogbn-arxiv LLM explanations"
-                "and predictions in default. The llm explanation and"
-                "prediction of each node is not specified."
-                "Please pass in 'llm_explanation' and 'llm_prediction' when"
-                "convert your dataset to Text Attribute Graph Dataset")
 
     def save_node_text(self, text: List[str]) -> None:
         node_text_path = osp.join(self.root, 'raw', 'node-text.csv.gz')

torch_geometric/llm/models/sentence_transformer.py

@@ -112,6 +112,19 @@ class SentenceTransformer(torch.nn.Module):
         output_device: Optional[Union[torch.device, str]] = None,
         verbose=False,
     ) -> Tensor:
+        r"""Main function for users. Converts strings to embeddings.
+
+        Args:
+            text (List[str]): List of strings to embed.
+            batch_size (int, optional): How many strings to process.
+                Defaults to processing all at once, but this may lead to
+                OOM errors. (default: obj:`None`)
+            output_device (Union[torch.device, str], optional):
+                By default outputs cpu pytorch tensor, but can choose
+                to output to specific cuda devices. (default: obj:`None`)
+            verbose (bool, optional): Controls the verbosity of outputs.
+                (default: obj:`False`)
+        """
         is_empty = len(text) == 0
         text = ['dummy'] if is_empty else text
 

torch_geometric/llm/utils/backend_utils.py

@@ -408,7 +408,8 @@ def make_pcst_filter(triples: List[Tuple[str, str,
         :return: Retrieved graph/query data
         """
         # PCST relies on numpy and pcst_fast pypi libs, hence to("cpu")
-        q_emb = model.encode([query]).to("cpu")
+        with torch.no_grad():
+            q_emb = model.encode([query]).to("cpu")
         textual_nodes = [(int(i), full_textual_nodes[i])
                          for i in graph["node_idx"]]
         textual_nodes = DataFrame(textual_nodes,

torch_geometric/llm/utils/vectorrag.py

@@ -65,7 +65,8 @@ class DocumentRetriever(VectorRetriever):
             List[str]: Documents retrieved from the vector database.
         """
         if isinstance(query, str):
-            query_enc = self.encoder(query, **self.model_kwargs)
+            with torch.no_grad():
+                query_enc = self.encoder(query, **self.model_kwargs)
         else:
             query_enc = query
 

torch_geometric/nn/conv/cugraph/gat_conv.py

@@ -26,6 +26,9 @@ class CuGraphGATConv(CuGraphModule):  # pragma: no cover
     :class:`~torch_geometric.nn.conv.GATConv` based on the :obj:`cugraph-ops`
     package that fuses message passing computation for accelerated execution
     and lower memory footprint.
+    The current method to enable :obj:`cugraph-ops`
+    is to use `The NVIDIA PyG Container
+    <https://catalog.ngc.nvidia.com/orgs/nvidia/containers/pyg>`_.
     """
     def __init__(
         self,
@@ -67,6 +70,7 @@ class CuGraphGATConv(CuGraphModule):  # pragma: no cover
         self,
         x: Tensor,
         edge_index: EdgeIndex,
+        edge_attr: Tensor,
         max_num_neighbors: Optional[int] = None,
     ) -> Tensor:
         graph = self.get_cugraph(edge_index, max_num_neighbors)
@@ -75,10 +79,12 @@ class CuGraphGATConv(CuGraphModule):  # pragma: no cover
 
         if LEGACY_MODE:
             out = GATConvAgg(x, self.att, graph, self.heads, 'LeakyReLU',
-                             self.negative_slope, False, self.concat)
+                             self.negative_slope, False, self.concat,
+                             edge_feat=edge_attr)
         else:
             out = GATConvAgg(x, self.att, graph, self.heads, 'LeakyReLU',
-                             self.negative_slope, self.concat)
+                             self.negative_slope, self.concat,
+                             edge_feat=edge_attr)
 
         if self.bias is not None:
             out = out + self.bias

torch_geometric/nn/conv/cugraph/rgcn_conv.py

@@ -29,6 +29,9 @@ class CuGraphRGCNConv(CuGraphModule):  # pragma: no cover
     :class:`~torch_geometric.nn.conv.RGCNConv` based on the :obj:`cugraph-ops`
     package that fuses message passing computation for accelerated execution
     and lower memory footprint.
+    The current method to enable :obj:`cugraph-ops`
+    is to use `The NVIDIA PyG Container
+    <https://catalog.ngc.nvidia.com/orgs/nvidia/containers/pyg>`_.
     """
     def __init__(self, in_channels: int, out_channels: int, num_relations: int,
                  num_bases: Optional[int] = None, aggr: str = 'mean',

torch_geometric/nn/conv/cugraph/sage_conv.py

@@ -27,6 +27,9 @@ class CuGraphSAGEConv(CuGraphModule):  # pragma: no cover
     :class:`~torch_geometric.nn.conv.SAGEConv` based on the :obj:`cugraph-ops`
     package that fuses message passing computation for accelerated execution
     and lower memory footprint.
+    The current method to enable :obj:`cugraph-ops`
+    is to use `The NVIDIA PyG Container
+    <https://catalog.ngc.nvidia.com/orgs/nvidia/containers/pyg>`_.
     """
     def __init__(
         self,

torch_geometric/nn/model_hub.py

@@ -144,10 +144,10 @@ class PyGModelHubMixin(ModelHubMixin):
         revision,
         cache_dir,
         force_download,
-        proxies,
-        resume_download,
         local_files_only,
         token,
+        proxies=None,
+        resume_download=False,
         dataset_name='',
         model_name='',
         map_location='cpu',
@@ -165,8 +165,6 @@ class PyGModelHubMixin(ModelHubMixin):
                 revision=revision,
                 cache_dir=cache_dir,
                 force_download=force_download,
-                proxies=proxies,
-                resume_download=resume_download,
                 token=token,
                 local_files_only=local_files_only,
             )
@@ -188,8 +186,6 @@ class PyGModelHubMixin(ModelHubMixin):
         cls,
         pretrained_model_name_or_path: str,
         force_download: bool = False,
-        resume_download: bool = False,
-        proxies: Optional[Dict] = None,
         token: Optional[Union[str, bool]] = None,
         cache_dir: Optional[str] = None,
         local_files_only: bool = False,
@@ -215,13 +211,6 @@ class PyGModelHubMixin(ModelHubMixin):
                 (re-)download of the model weights and configuration files,
                 overriding the cached versions if they exist.
                 (default: :obj:`False`)
-            resume_download (bool, optional): Whether to delete incompletely
-                received files. Will attempt to resume the download if such a
-                file exists. (default: :obj:`False`)
-            proxies (Dict[str, str], optional): A dictionary of proxy servers
-                to use by protocol or endpoint, *e.g.*,
-                :obj:`{'http': 'foo.bar:3128', 'http://host': 'foo.bar:4012'}`.
-                The proxies are used on each request. (default: :obj:`None`)
             token (str or bool, optional): The token to use as HTTP bearer
                 authorization for remote files. If set to :obj:`True`, will use
                 the token generated when running :obj:`transformers-cli login`
@@ -239,8 +228,6 @@ class PyGModelHubMixin(ModelHubMixin):
         return super().from_pretrained(
             pretrained_model_name_or_path,
             force_download=force_download,
-            resume_download=resume_download,
-            proxies=proxies,
             use_auth_token=token,
             cache_dir=cache_dir,
             local_files_only=local_files_only,

torch_geometric/nn/pool/cluster_pool.py

@@ -20,8 +20,7 @@ class UnpoolInfo(NamedTuple):
 
 class ClusterPooling(torch.nn.Module):
     r"""The cluster pooling operator from the `"Edge-Based Graph Component
-    Pooling" <paper url>`_ paper.
-
+    Pooling" <https://arxiv.org/abs/2409.11856>`_ paper.
     :class:`ClusterPooling` computes a score for each edge.
     Based on the selected edges, graph clusters are calculated and compressed
     to one node using the injective :obj:`"sum"` aggregation function.