pyg-nightly 2.7.0.dev20250919__py3-none-any.whl → 2.7.0.dev20250921__py3-none-any.whl

{pyg_nightly-2.7.0.dev20250919.dist-info → pyg_nightly-2.7.0.dev20250921.dist-info}/METADATA

@@ -1,15 +1,14 @@
 Metadata-Version: 2.4
 Name: pyg-nightly
-Version: 2.7.0.dev20250919
+Version: 2.7.0.dev20250921
 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>
-Requires-Python: >=3.9
+Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-Expression: MIT
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Programming Language :: Python
-Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
@@ -45,7 +44,6 @@ Requires-Dist: networkx ; extra == "full"
 Requires-Dist: numba<0.60.0 ; extra == "full"
 Requires-Dist: opt_einsum ; extra == "full"
 Requires-Dist: pandas ; extra == "full"
-Requires-Dist: pgmpy ; extra == "full"
 Requires-Dist: pynndescent ; extra == "full"
 Requires-Dist: pytorch-memlab ; extra == "full"
 Requires-Dist: rdflib ; extra == "full"
@@ -91,14 +89,21 @@ Provides-Extra: test
 
 ______________________________________________________________________
 
+<div align="center">
+
 [![PyPI Version][pypi-image]][pypi-url]
-[![Testing Status][testing-image]][testing-url]
-[![Linting Status][linting-image]][linting-url]
-[![Docs Status][docs-image]][docs-url]
-[![Contributing][contributing-image]][contributing-url]
+[![PyPI Download][pypi-download-image]][pypi-download-url]
 [![Slack][slack-image]][slack-url]
+[![Contributing][contributing-image]][contributing-url]
+
+**[Documentation](https://pytorch-geometric.readthedocs.io)** |
+**[PyG 1.0 Paper](https://arxiv.org/abs/1903.02428)** |
+**[PyG 2.0 Paper](https://arxiv.org/abs/2507.16991)** |
+**[Colab Notebooks](https://pytorch-geometric.readthedocs.io/en/latest/get_started/colabs.html)** |
+**[External Resources](https://pytorch-geometric.readthedocs.io/en/latest/external/resources.html)** |
+**[OGB Examples](https://github.com/snap-stanford/ogb/tree/master/examples)**
 
-**[Documentation](https://pytorch-geometric.readthedocs.io)** | **[PyG 1.0 Paper](https://arxiv.org/abs/1903.02428)** | **[PyG 2.0 Paper](https://arxiv.org/abs/2507.16991)** | **[Colab Notebooks](https://pytorch-geometric.readthedocs.io/en/latest/get_started/colabs.html)** | **[External Resources](https://pytorch-geometric.readthedocs.io/en/latest/external/resources.html)** | **[OGB Examples](https://github.com/snap-stanford/ogb/tree/master/examples)**
+</div>
 
 **PyG** *(PyTorch Geometric)* is a library built upon [PyTorch](https://pytorch.org/) to easily write and train Graph Neural Networks (GNNs) for a wide range of applications related to structured data.
 
@@ -421,7 +426,7 @@ These approaches have been implemented in PyG, and can benefit from the above GN
 
 ## Installation
 
-PyG is available for Python 3.9 to Python 3.13.
+PyG is available for Python 3.10 to Python 3.13.
 
 From **PyG 2.3** onwards, you can install and use PyG **without any external library** required except for PyTorch.
 For this, simply run
@@ -546,16 +551,12 @@ If you notice anything unexpected, please open an [issue](https://github.com/pyg
 If you have any questions or are missing a specific feature, feel free [to discuss them with us](https://github.com/pyg-team/pytorch_geometric/discussions).
 We are motivated to constantly make PyG even better.
 
-[contributing-image]: https://img.shields.io/badge/contributions-welcome-brightgreen.svg?style=flat
+[contributing-image]: https://img.shields.io/badge/contributions-welcome-brightgreen.svg?style=flat&color=4B26A4
 [contributing-url]: https://github.com/pyg-team/pytorch_geometric/blob/master/.github/CONTRIBUTING.md
-[docs-image]: https://readthedocs.org/projects/pytorch-geometric/badge/?version=latest
-[docs-url]: https://pytorch-geometric.readthedocs.io/en/latest
-[linting-image]: https://github.com/pyg-team/pytorch_geometric/actions/workflows/linting.yml/badge.svg
-[linting-url]: https://github.com/pyg-team/pytorch_geometric/actions/workflows/linting.yml
-[pypi-image]: https://badge.fury.io/py/torch-geometric.svg
+[pypi-download-image]: https://img.shields.io/pypi/dm/torch_geometric?color=4B26A4
+[pypi-download-url]: https://pepy.tech/projects/torch_geometric
+[pypi-image]: https://img.shields.io/pypi/pyversions/torch-geometric?color=4B26A4
 [pypi-url]: https://pypi.python.org/pypi/torch-geometric
-[slack-image]: https://img.shields.io/badge/slack-pyg-brightgreen
+[slack-image]: https://img.shields.io/badge/slack-join-white.svg?logo=slack&color=4B26A4
 [slack-url]: https://data.pyg.org/slack.html
-[testing-image]: https://github.com/pyg-team/pytorch_geometric/actions/workflows/testing.yml/badge.svg
-[testing-url]: https://github.com/pyg-team/pytorch_geometric/actions/workflows/testing.yml
 

{pyg_nightly-2.7.0.dev20250919.dist-info → pyg_nightly-2.7.0.dev20250921.dist-info}/RECORD

@@ -1,9 +1,9 @@
-torch_geometric/__init__.py,sha256=OLGPhTHC1wmAq6rg69s1sbJUFuptQaVPvG0ggAYNOlM,2292
+torch_geometric/__init__.py,sha256=pOD9vZjRGqoUzFw5_-UNQVsobbiDjoaicP9Jw5mj9jE,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
 torch_geometric/config_mixin.py,sha256=hOTJu5LLVrEAZ6Pjt4ScLDLKv9aHbfAzF_3ufwKgO4I,4301
-torch_geometric/config_store.py,sha256=zdMzlgBpUmBkPovpYQh5fMNwTZLDq2OneqX47QEx7zk,16818
+torch_geometric/config_store.py,sha256=Lj5pY_fFamF6pr5XhaKcYXZ3ecUTFNHWEprnBwaNbso,16801
 torch_geometric/debug.py,sha256=cLyH9OaL2v7POyW-80b19w-ctA7a_5EZsS4aUF1wc2U,1295
 torch_geometric/deprecation.py,sha256=gN65uX23c3miRPOpQzxcRS_QDUpD3B-qVKD6y6GX8Yw,872
 torch_geometric/device.py,sha256=tU5-_lBNVbVHl_kUmWPwiG5mQ1pyapwMF4JkmtNN3MM,1224
@@ -19,7 +19,7 @@ torch_geometric/logging.py,sha256=HmHHLiCcM64k-6UYNOSfXPIeSGNAyiGGcn8cD8tlyuQ,85
 torch_geometric/resolver.py,sha256=fn-_6mCpI2xv7eDZnIFcYrHOn0IrwbkWFLDb9laQrWI,1270
 torch_geometric/seed.py,sha256=MJLbVwpb9i8mK3oi32sS__Cq-dRq_afTeoOL_HoA9ko,372
 torch_geometric/template.py,sha256=rqjDWgcSAgTCiV4bkOjWRPaO4PpUdC_RXigzxxBqAu8,1060
-torch_geometric/typing.py,sha256=PenHvJZ2ZQ0V6t5hYypcZq8mQ47upgSlVTqHPy6QvLc,15704
+torch_geometric/typing.py,sha256=Kj0R-aw81aY6JE1pbsG_7Jf830tect31uzibDFsjSPc,15684
 torch_geometric/warnings.py,sha256=SB9dWGovX_KKcxqsOrdTDvSb_j0NoB5vPGnK2vg0jVw,727
 torch_geometric/contrib/__init__.py,sha256=To_lDofgM7sogKEYOICIXei7Njuk-Vkfm-OFhPIdaLo,366
 torch_geometric/contrib/datasets/__init__.py,sha256=lrGnWsEiJf5zsBRmshGZZFN_uYR2ezDjbj9n9nCpvtk,23
@@ -36,7 +36,7 @@ torch_geometric/data/collate.py,sha256=tOUvttXoEo-bOvJx_qMivJq2JqOsB9iDdjovtiyys
 torch_geometric/data/data.py,sha256=-E6el1knNgSJyapV8KUk2aRRHOfvwEvjUFfe_BapLfc,47490
 torch_geometric/data/database.py,sha256=K3KLefYVfsBN9HRItgFZNkbUIllfDt4ueauBFxk3Rxk,23106
 torch_geometric/data/datapipes.py,sha256=9_Cq3j_7LIF4plQFzbLaqyy0LcpKdAic6yiKgMqSX9A,3083
-torch_geometric/data/dataset.py,sha256=AaJH0N9eZgvxX0ljyTH8cXutKJ0AGFAyE-H4Sw9D51w,16834
+torch_geometric/data/dataset.py,sha256=-B9lXmpJ5-yhLZ-38PzKaaDeFZ1y-hfsTn-bVrnzrYA,16886
 torch_geometric/data/download.py,sha256=kcesTu6jlgmCeePpOxDQOnVhxB_GuZ9iu9ds72KEORc,1889
 torch_geometric/data/extract.py,sha256=DMG8_6ps4O5xKfkb7j1gUBX_jlWpFdmz6OLY2jBSEx4,2339
 torch_geometric/data/feature_store.py,sha256=pl2pJL25wqzEZnNZbW8c8Ee_yH0DnE2AK8TioTWZV-g,20045
@@ -118,7 +118,7 @@ torch_geometric/datasets/medshapenet.py,sha256=eCBCXKpueweCwDSf_Q4_MwVA3IbJd04FS
 torch_geometric/datasets/mixhop_synthetic_dataset.py,sha256=4NNvTHUvvV6pcqQCyVDS5XhppXUeF2H9GTfFoc49eyU,3951
 torch_geometric/datasets/mnist_superpixels.py,sha256=o2ArbZ0_OE0u8VCaHmWwvngESlOFr9oM9dSEP_tjAS4,3340
 torch_geometric/datasets/modelnet.py,sha256=rqR-e75lC8PS_IX7VlNbo2Az9IWfqMNvDp8rmQCp-LE,5357
-torch_geometric/datasets/molecule_gpt_dataset.py,sha256=d6V8_Qy1Y2nt9hFhn7Re1omFw5Tf_uhv13QM0Vg76eg,19091
+torch_geometric/datasets/molecule_gpt_dataset.py,sha256=DUzX1h7a0qsIhUVzLyNb5qarxZYFrxBr4bsQJ7vsJrk,19096
 torch_geometric/datasets/molecule_net.py,sha256=pMzaJzd-LbBncZ0VoC87HfA8d1F4NwCWTb5YKvLM890,7404
 torch_geometric/datasets/movie_lens.py,sha256=M4Bu0Xus8IkW8GYzjxPxSdPXNbcCCx9cu6cncxBvLx8,4033
 torch_geometric/datasets/movie_lens_100k.py,sha256=eTpBAteM3jqTEtiwLxmhVj4r8JvftvPx8Hvs-3ZIHlU,6057
@@ -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=qTnwr2N1tbWYeLGbItfv70UxQ3n1rKesjeVU3kcOCP8,14757
+torch_geometric/datasets/tag_dataset.py,sha256=jslijGCh37ip2YkrQLyvbk-1QRJ3yqFpmzuQSxckXrE,19402
 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
@@ -181,7 +181,7 @@ torch_geometric/datasets/motif_generator/grid.py,sha256=Pcv3r80nfzqpBvRTAJT_J0Dp
 torch_geometric/datasets/motif_generator/house.py,sha256=C_E2EgeqXEB9CHKRd9V5Jji4lFPpJb_3c41vYSk9Gcs,814
 torch_geometric/datasets/utils/__init__.py,sha256=At_dId4MdpzAkDS_7Mc6I7XlkThbL0AbVzHC_92lcjA,182
 torch_geometric/datasets/utils/cheatsheet.py,sha256=M55Bj64cjMVqDNoIq1shUVeU2ngoxpEjhdtyqw7Sd_k,1835
-torch_geometric/distributed/__init__.py,sha256=NNCGXbDTAW5xoJgSr-PK0VYEnT8UCI7SoZXc16fjuxQ,589
+torch_geometric/distributed/__init__.py,sha256=FUsRoS28c7XfnwlA9yF4m2xZWos5TdpQSuY3Bm48vz8,1108
 torch_geometric/distributed/dist_context.py,sha256=n34e2HU-TxmK6DrOpb5lWZu_xg1To1IFrXH4ueF_Jhg,418
 torch_geometric/distributed/dist_link_neighbor_loader.py,sha256=wM9heZmStrPSW7eo9qWusKdI_lVkDkLlda8ILBqC2c8,4933
 torch_geometric/distributed/dist_loader.py,sha256=Gjvl5Ck8YrFN6YmCWEFWVqLEwI1hog-rWj2Sk_zqYC0,6504
@@ -308,10 +308,10 @@ torch_geometric/loader/prefetch.py,sha256=z30TIcu3_6ZubllUOwNLunlq4RyQdFj36vPE5Q
 torch_geometric/loader/random_node_loader.py,sha256=rCmRXYv70SPxBo-Oh049eFEWEZDV7FmlRPzmjcoirXQ,2196
 torch_geometric/loader/shadow.py,sha256=_hCspYf9SlJYX0lqEjxFec9e9t1iMScNThOoWR1wQGM,4173
 torch_geometric/loader/temporal_dataloader.py,sha256=Z7L_rYdl6SYBQXAgtr18FVcmfMH9kP1fBWrc2W63g2c,2250
-torch_geometric/loader/utils.py,sha256=3hzKzIgB52QIZu7Jdn4JeXZaegIJinIQfIUP9DrUWUQ,14903
+torch_geometric/loader/utils.py,sha256=DgGHK6kNu7ZZIZuaT0Ya_4rUctBMMKyBBSdHhuU389w,14903
 torch_geometric/loader/zip_loader.py,sha256=3lt10fD15Rxm1WhWzypswGzCEwUz4h8OLCD1nE15yNg,3843
 torch_geometric/metrics/__init__.py,sha256=3krvDobW6vV5yHTjq2S2pmOXxNfysNG26muq7z48e94,699
-torch_geometric/metrics/link_pred.py,sha256=1_hE3KiRqAdZLI6QuUbjgyFC__mTyFu_RimM3bD8wRw,31678
+torch_geometric/metrics/link_pred.py,sha256=bacmFGn7rm0iF2wOJdAW-iTZ04bOuiS-7ur2K-MZKlA,31684
 torch_geometric/nn/__init__.py,sha256=tTEKDy4vpjPNKyG1Vg9GIx7dVFJuQtBoh2M19ascGpo,880
 torch_geometric/nn/data_parallel.py,sha256=YiybTWoSFyfSzlXAamZ_-y1f7B6tvDEFHOuy_AyJz9Q,4761
 torch_geometric/nn/encoding.py,sha256=82fpwyOx0-STFSAJ5AzG0p2WFC9u1M4KgmKIql8hSLc,3634
@@ -453,7 +453,7 @@ torch_geometric/nn/models/__init__.py,sha256=7eRlAR93pltDfLEcsTJaaK67mVFezAIjg0V
 torch_geometric/nn/models/attentive_fp.py,sha256=1z3iTV2O5W9tqHFAdno8FeBFeXmuG-TDZk4lwwVh3Ac,6634
 torch_geometric/nn/models/attract_repel.py,sha256=h9OyogT0NY0xiT0DkpJHMxH6ZUmo8R-CmwZdKEwq8Ek,5277
 torch_geometric/nn/models/autoencoder.py,sha256=nGje-zty78Y3hxOJ9o0_6QziJjOvBlknk6z0_fDQwQU,10770
-torch_geometric/nn/models/basic_gnn.py,sha256=PGa0RUMyvrNy_5yRI2jX_zwPsmZXwOQWfsWvxOiHsSk,31225
+torch_geometric/nn/models/basic_gnn.py,sha256=tp7qbHKn_uO1CBaEiW79zaBDAD-fR88E8ffJpdDYr9w,31261
 torch_geometric/nn/models/captum.py,sha256=vPN85_HDMTNcw-rKXAtYY-vT2SbHdf4CFtkseqYsnHg,3972
 torch_geometric/nn/models/correct_and_smooth.py,sha256=wmq-US2r4ocd0a661R8YeDiBeVtILOjdN-4swIth9BQ,6827
 torch_geometric/nn/models/deep_graph_infomax.py,sha256=yXSZ4mCrq4Dcvl1muzkxEWH4Lo525J4cYuAXpGs55IY,4137
@@ -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.dev20250919.dist-info/licenses/LICENSE,sha256=ic-27cMJc1kWoMEYncz3Ya3Ur2Bi3bNLWib2DT763-o,1067
-pyg_nightly-2.7.0.dev20250919.dist-info/WHEEL,sha256=G2gURzTEtmeR8nrdXUJfNiB3VYVxigPQ-bEQujpNiNs,82
-pyg_nightly-2.7.0.dev20250919.dist-info/METADATA,sha256=IfaNYkgI-HE5ar5wS1k5XG9esWAh643uI1uvCOX7ChY,64145
-pyg_nightly-2.7.0.dev20250919.dist-info/RECORD,,
+pyg_nightly-2.7.0.dev20250921.dist-info/licenses/LICENSE,sha256=ic-27cMJc1kWoMEYncz3Ya3Ur2Bi3bNLWib2DT763-o,1067
+pyg_nightly-2.7.0.dev20250921.dist-info/WHEEL,sha256=G2gURzTEtmeR8nrdXUJfNiB3VYVxigPQ-bEQujpNiNs,82
+pyg_nightly-2.7.0.dev20250921.dist-info/METADATA,sha256=A3uqoYW6Tuh_CSAyaqwO_WS0CY4l-r6_kQZAu_PYo_U,63680
+pyg_nightly-2.7.0.dev20250921.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.dev20250919'
+__version__ = '2.7.0.dev20250921'
 
 __all__ = [
     'Index',

torch_geometric/config_store.py

@@ -168,7 +168,7 @@ def map_annotation(
         assert origin is not None
         args = tuple(map_annotation(a, mapping) for a in args)
         if type(annotation).__name__ == 'GenericAlias':
-            # If annotated with `list[...]` or `dict[...]` (>= Python 3.10):
+            # If annotated with `list[...]` or `dict[...]`:
             annotation = origin[args]
         else:
             # If annotated with `typing.List[...]` or `typing.Dict[...]`:

torch_geometric/data/dataset.py

@@ -236,8 +236,8 @@ class Dataset(torch.utils.data.Dataset):
 
     def _process(self):
         f = osp.join(self.processed_dir, 'pre_transform.pt')
-        if osp.exists(f) and torch.load(f, weights_only=False) != _repr(
-                self.pre_transform):
+        if not self.force_reload and osp.exists(f) and torch.load(
+                f, weights_only=False) != _repr(self.pre_transform):
             warnings.warn(
                 "The `pre_transform` argument differs from the one used in "
                 "the pre-processed version of this dataset. If you want to "
@@ -246,8 +246,8 @@ class Dataset(torch.utils.data.Dataset):
                 stacklevel=2)
 
         f = osp.join(self.processed_dir, 'pre_filter.pt')
-        if osp.exists(f) and torch.load(f, weights_only=False) != _repr(
-                self.pre_filter):
+        if not self.force_reload and osp.exists(f) and torch.load(
+                f, weights_only=False) != _repr(self.pre_filter):
             warnings.warn(
                 "The `pre_filter` argument differs from the one used in "
                 "the pre-processed version of this dataset. If you want to "

torch_geometric/datasets/molecule_gpt_dataset.py

@@ -174,7 +174,7 @@ def extract_name(
 class MoleculeGPTDataset(InMemoryDataset):
     r"""The dataset from the `"MoleculeGPT: Instruction Following Large
     Language Models for Molecular Property Prediction"
-    <https://ai4d3.github.io/papers/34.pdf>`_ paper.
+    <https://ai4d3.github.io/2023/papers/34.pdf>`_ paper.
 
     Args:
         root (str): Root directory where the dataset should be saved.

torch_geometric/datasets/tag_dataset.py

@@ -1,3 +1,4 @@
+import csv
 import os
 import os.path as osp
 from collections.abc import Sequence
@@ -10,6 +11,7 @@ from tqdm import tqdm
 
 from torch_geometric.data import InMemoryDataset, download_google_url
 from torch_geometric.data.data import BaseData
+from torch_geometric.io import fs
 
 try:
     from pandas import DataFrame, read_csv
@@ -22,14 +24,16 @@ IndexType = Union[slice, Tensor, np.ndarray, Sequence]
 
 class TAGDataset(InMemoryDataset):
     r"""The Text Attributed Graph datasets from the
-    `"Learning on Large-scale Text-attributed Graphs via Variational Inference
-    " <https://arxiv.org/abs/2210.14709>`_ paper.
+    `"Learning on Large-scale Text-attributed Graphs via Variational Inference"
+    <https://arxiv.org/abs/2210.14709>`_ paper and `"Harnessing Explanations:
+    LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation
+    Learning" <https://arxiv.org/abs/2305.19523>`_ paper.
     This dataset is aiming on transform `ogbn products`, `ogbn arxiv`
     into Text Attributed Graph that each node in graph is associate with a
-    raw text, that dataset can be adapt to DataLoader (for LM training) and
-    NeighborLoader(for GNN training). In addition, this class can be use as a
-    wrapper class by convert a InMemoryDataset with Tokenizer and text into
-    Text Attributed Graph.
+    raw text, LLM prediction and explanation, that dataset can be adapt to
+    DataLoader (for LM training) and NeighborLoader(for GNN training).
+    In addition, this class can be use as a wrapper class by convert a
+    InMemoryDataset with Tokenizer and text into Text Attributed Graph.
 
     Args:
         root (str): Root directory where the dataset should be saved.
@@ -51,22 +55,35 @@ class TAGDataset(InMemoryDataset):
             or not, default: False
         force_reload (bool): default: False
     .. note::
-        See `example/llm_plus_gnn/glem.py` for example usage
+        See `example/llm/glem.py` for example usage
     """
     raw_text_id = {
         'ogbn-arxiv': '1g3OOVhRyiyKv13LY6gbp8GLITocOUr_3',
         'ogbn-products': '1I-S176-W4Bm1iPDjQv3hYwQBtxE0v8mt'
     }
 
-    def __init__(self, root: str, dataset: InMemoryDataset,
-                 tokenizer_name: str, text: Optional[List[str]] = None,
-                 split_idx: Optional[Dict[str, Tensor]] = None,
-                 tokenize_batch_size: int = 256, token_on_disk: bool = False,
-                 text_on_disk: bool = False,
-                 force_reload: bool = False) -> None:
+    llm_prediction_url = 'https://github.com/XiaoxinHe/TAPE/raw/main/gpt_preds'
+
+    llm_explanation_id = {
+        'ogbn-arxiv': '1o8n2xRen-N_elF9NQpIca0iCHJgEJbRQ',
+    }
+
+    def __init__(
+        self,
+        root: str,
+        dataset: InMemoryDataset,
+        tokenizer_name: str,
+        text: Optional[List[str]] = None,
+        split_idx: Optional[Dict[str, Tensor]] = None,
+        tokenize_batch_size: int = 256,
+        token_on_disk: bool = False,
+        text_on_disk: bool = False,
+        force_reload: bool = False,
+    ) -> None:
         # list the vars you want to pass in before run download & process
         self.name = dataset.name
         self.text = text
+        self.llm_prediction_topk = 5
         self.tokenizer_name = tokenizer_name
         from transformers import AutoTokenizer
         self.tokenizer = AutoTokenizer.from_pretrained(tokenizer_name)
@@ -93,8 +110,9 @@ class TAGDataset(InMemoryDataset):
                              "is_gold mask, please pass splited index "
                              "in format of dictionaty with 'train', 'valid' "
                              "'test' index tensor to 'split_idx'")
-        if text is not None and text_on_disk:
-            self.save_node_text(text)
+        if text_on_disk:
+            if text is not None:
+                self.save_node_text(text)
         self.text_on_disk = text_on_disk
         # init will call download and process
         super().__init__(self.root, transform=None, pre_transform=None,
@@ -119,6 +137,10 @@ 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.__num_classes__ = dataset.num_classes
 
     @property
@@ -146,6 +168,19 @@ class TAGDataset(InMemoryDataset):
             self._token = self.tokenize_graph()
         return self._token
 
+    @property
+    def llm_explanation_token(self) -> Dict[str, Tensor]:
+        if self._llm_explanation_token is None:  # lazy load
+            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
+            self._all_token = self.tokenize_graph(text_type='all')
+        return self._all_token
+
     # load is_gold after init
     @property
     def is_gold(self) -> Tensor:
@@ -194,10 +229,17 @@ class TAGDataset(InMemoryDataset):
                                             folder=f'{self.root}/raw',
                                             filename='node-text.csv.gz',
                                             log=True)
-        text_df = read_csv(raw_text_path)
-        self.text = list(text_df['text'])
+        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)
 
     def process(self) -> None:
+        # process Title and Abstraction
         if osp.exists(osp.join(self.root, 'raw', 'node-text.csv.gz')):
             text_df = read_csv(osp.join(self.root, 'raw', 'node-text.csv.gz'))
             self.text = list(text_df['text'])
@@ -212,6 +254,42 @@ class TAGDataset(InMemoryDataset):
                              "The raw text of each node is not specified"
                              "Please pass in 'text' when convert your dataset "
                              "to Text Attribute Graph Dataset")
+        # process LLM explanation and prediction
+        llm_explanation_path = f'{self.raw_dir}/node-gpt-response.csv.gz'
+        llm_prediction_path = f'{self.raw_dir}/{self.name}.csv'
+        if osp.exists(llm_explanation_path) and osp.exists(
+                llm_prediction_path):
+            # load LLM explanation
+            self.llm_explanation = list(read_csv(llm_explanation_path)['text'])
+            # load LLM prediction
+            preds = []
+            with open(llm_prediction_path) as file:
+                reader = csv.reader(file)
+                for row in reader:
+                    inner_list = []
+                    for value in row:
+                        inner_list.append(int(value))
+                    preds.append(inner_list)
+
+            pl = torch.zeros(len(preds), self.llm_prediction_topk,
+                             dtype=torch.long)
+            for i, pred in enumerate(preds):
+                pl[i][:len(pred)] = torch.tensor(
+                    pred[:self.llm_prediction_topk], dtype=torch.long) + 1
+        elif self.name in self.llm_explanation_id:
+            self.download()
+        else:
+            print(
+                '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')
@@ -224,22 +302,39 @@ class TAGDataset(InMemoryDataset):
             text_df.to_csv(osp.join(node_text_path), compression='gzip',
                            index=False)
 
-    def tokenize_graph(self, batch_size: int = 256) -> Dict[str, Tensor]:
+    def tokenize_graph(self, batch_size: int = 256,
+                       text_type: str = 'raw_text') -> Dict[str, Tensor]:
         r"""Tokenizing the text associate with each node, running in cpu.
 
         Args:
             batch_size (Optional[int]): batch size of list of text for
                 generating emebdding
+            text_type (Optional[str]): type of text
         Returns:
             Dict[str, torch.Tensor]: tokenized graph
         """
+        assert text_type in ['raw_text', 'llm_explanation', 'all']
+        if text_type == 'raw_text':
+            _text = self.text
+        elif text_type == 'llm_explanation':
+            _text = self.llm_explanation
+        elif text_type == 'all':
+            if self.text is None or self.llm_explanation is None:
+                raise ValueError("The TAGDataset need text and llm explanation"
+                                 "for tokenizing all text")
+            _text = [
+                f'{raw_txt} Explanation: {exp_txt}'
+                for raw_txt, exp_txt in zip(self.text, self.llm_explanation)
+            ]
+
         data_len = 0
-        if self.text is not None:
-            data_len = len(self.text)
+        if _text is not None:
+            data_len = len(_text)
         else:
             raise ValueError("The TAGDataset need text for tokenization")
         token_keys = ['input_ids', 'token_type_ids', 'attention_mask']
-        path = os.path.join(self.processed_dir, 'token', self.tokenizer_name)
+        path = os.path.join(self.processed_dir, 'token', text_type,
+                            self.tokenizer_name)
         # Check if the .pt files already exist
         token_files_exist = any(
             os.path.exists(os.path.join(path, f'{k}.pt')) for k in token_keys)
@@ -256,12 +351,12 @@ class TAGDataset(InMemoryDataset):
         all_encoded_token = {k: [] for k in token_keys}
         pbar = tqdm(total=data_len)
 
-        pbar.set_description('Tokenizing Text Attributed Graph')
+        pbar.set_description(f'Tokenizing Text Attributed Graph {text_type}')
         for i in range(0, data_len, batch_size):
             end_index = min(data_len, i + batch_size)
-            token = self.tokenizer(self.text[i:min(i + batch_size, data_len)],
-                                   padding='max_length', truncation=True,
-                                   max_length=512, return_tensors="pt")
+            token = self.tokenizer(_text[i:end_index], padding='max_length',
+                                   truncation=True, max_length=512,
+                                   return_tensors="pt")
             for k in token.keys():
                 all_encoded_token[k].append(token[k])
             pbar.update(end_index - i)
@@ -289,10 +384,18 @@ class TAGDataset(InMemoryDataset):
 
         Args:
             tag_dataset (TAGDataset): the parent dataset
+            text_type (str): type of text
         """
-        def __init__(self, tag_dataset: 'TAGDataset') -> None:
+        def __init__(self, tag_dataset: 'TAGDataset',
+                     text_type: str = 'raw_text') -> None:
+            assert text_type in ['raw_text', 'llm_explanation', 'all']
             self.tag_dataset = tag_dataset
-            self.token = tag_dataset.token
+            if text_type == 'raw_text':
+                self.token = tag_dataset.token
+            elif text_type == 'llm_explanation':
+                self.token = tag_dataset.llm_explanation_token
+            elif text_type == 'all':
+                self.token = tag_dataset.all_token
             assert tag_dataset._data is not None
             self._data = tag_dataset._data
 
@@ -312,7 +415,8 @@ class TAGDataset(InMemoryDataset):
 
         # for LM training
         def __getitem__(
-                self, node_id: IndexType
+            self,
+            node_id: IndexType,
         ) -> Dict[str, Union[Tensor, Dict[str, Tensor]]]:
             r"""This function will override the function in
             torch.utils.data.Dataset, and will be called when you
@@ -343,8 +447,8 @@ class TAGDataset(InMemoryDataset):
         def __repr__(self) -> str:
             return f'{self.__class__.__name__}()'
 
-    def to_text_dataset(self) -> TextDataset:
+    def to_text_dataset(self, text_type: str = 'raw_text') -> TextDataset:
         r"""Factory Build text dataset from Text Attributed Graph Dataset
         each data point is node's associated text token.
         """
-        return TAGDataset.TextDataset(self)
+        return TAGDataset.TextDataset(self, text_type)

torch_geometric/distributed/__init__.py

@@ -1,3 +1,5 @@
+from warnings import warn
+
 from .dist_context import DistContext
 from .local_feature_store import LocalFeatureStore
 from .local_graph_store import LocalGraphStore
@@ -7,6 +9,17 @@ from .dist_loader import DistLoader
 from .dist_neighbor_loader import DistNeighborLoader
 from .dist_link_neighbor_loader import DistLinkNeighborLoader
 
+warn(
+    "`torch_geometric.distributed` has been deprecated since 2.7.0 and will "
+    "no longer be maintained. For distributed training, refer to our "
+    "tutorials on distributed training at "
+    "https://pytorch-geometric.readthedocs.io/en/latest/tutorial/distributed.html "  # noqa: E501
+    "or cuGraph examples at "
+    "https://github.com/rapidsai/cugraph-gnn/tree/main/python/cugraph-pyg/cugraph_pyg/examples",  # noqa: E501
+    stacklevel=2,
+    category=DeprecationWarning,
+)
+
 __all__ = classes = [
     'DistContext',
     'LocalFeatureStore',

torch_geometric/loader/utils.py

@@ -256,14 +256,6 @@ def filter_custom_hetero_store(
     # Construct a new `HeteroData` object:
     data = custom_cls() if custom_cls is not None else HeteroData()
 
-    # Filter edge storage:
-    # TODO support edge attributes
-    for attr in graph_store.get_all_edge_attrs():
-        key = attr.edge_type
-        if key in row_dict and key in col_dict:
-            edge_index = torch.stack([row_dict[key], col_dict[key]], dim=0)
-            data[attr.edge_type].edge_index = edge_index
-
     # Filter node storage:
     required_attrs = []
     for attr in feature_store.get_all_tensor_attrs():
@@ -280,6 +272,14 @@ def filter_custom_hetero_store(
     for i, attr in enumerate(required_attrs):
         data[attr.group_name][attr.attr_name] = tensors[i]
 
+    # Filter edge storage:
+    # TODO support edge attributes
+    for attr in graph_store.get_all_edge_attrs():
+        key = attr.edge_type
+        if key in row_dict and key in col_dict:
+            edge_index = torch.stack([row_dict[key], col_dict[key]], dim=0)
+            data[attr.edge_type].edge_index = edge_index
+
     return data
 
 

torch_geometric/metrics/link_pred.py

@@ -53,7 +53,7 @@ class LinkPredMetricData:
 
         # Flatten both prediction and ground-truth indices, and determine
         # overlaps afterwards via `torch.searchsorted`.
-        max_index = max(  # type: ignore
+        max_index = max(
             self.pred_index_mat.max()
             if self.pred_index_mat.numel() > 0 else 0,
             self.edge_label_index[1].max()
@@ -820,9 +820,10 @@ class LinkPredPersonalization(_LinkPredMetric):
             right = pred[col.cpu()].to(device)
 
             # Use offset to work around applying `isin` along a specific dim:
-            i = max(left.max(), right.max()) + 1  # type: ignore
-            i = torch.arange(0, i * row.size(0), i, device=device).view(-1, 1)
-            isin = torch.isin(left + i, right + i)
+            i = max(int(left.max()), int(right.max())) + 1
+            idx = torch.arange(0, i * row.size(0), i, device=device)
+            idx = idx.view(-1, 1)
+            isin = torch.isin(left + idx, right + idx)
 
             # Compute personalization via average inverse cosine similarity:
             cos = isin.sum(dim=-1) / pred.size(1)

torch_geometric/nn/models/basic_gnn.py

@@ -415,7 +415,8 @@ class GCN(BasicGNN):
             (default: :obj:`None`)
         jk (str, optional): The Jumping Knowledge mode. If specified, the model
             will additionally apply a final linear transformation to transform
-            node embeddings to the expected output feature dimensionality.
+            node embeddings to the expected output feature dimensionality,
+            while default will not.
             (:obj:`None`, :obj:`"last"`, :obj:`"cat"`, :obj:`"max"`,
             :obj:`"lstm"`). (default: :obj:`None`)
         **kwargs (optional): Additional arguments of

torch_geometric/typing.py

@@ -3,17 +3,12 @@ import os
 import sys
 import typing
 import warnings
-from typing import Any, Dict, List, Optional, Set, Tuple, Union
+from typing import Any, Dict, List, Optional, Set, Tuple, TypeAlias, Union
 
 import numpy as np
 import torch
 from torch import Tensor
 
-try:
-    from typing import TypeAlias  # type: ignore
-except ImportError:
-    from typing_extensions import TypeAlias
-
 WITH_PT20 = int(torch.__version__.split('.')[0]) >= 2
 WITH_PT21 = WITH_PT20 and int(torch.__version__.split('.')[1]) >= 1
 WITH_PT22 = WITH_PT20 and int(torch.__version__.split('.')[1]) >= 2
@@ -98,7 +93,7 @@ except Exception as e:
     WITH_CUDA_HASH_MAP = False
 
 if WITH_CPU_HASH_MAP:
-    CPUHashMap: TypeAlias = torch.classes.pyg.CPUHashMap
+    CPUHashMap: TypeAlias = torch.classes.pyg.CPUHashMap  # type: ignore[name-defined]  # noqa: E501
 else:
 
     class CPUHashMap:  # type: ignore
@@ -110,7 +105,7 @@ else:
 
 
 if WITH_CUDA_HASH_MAP:
-    CUDAHashMap: TypeAlias = torch.classes.pyg.CUDAHashMap
+    CUDAHashMap: TypeAlias = torch.classes.pyg.CUDAHashMap  # type: ignore[name-defined]  # noqa: E501
 else:
 
     class CUDAHashMap:  # type: ignore