PyPI - pyg-nightly - Versions diffs - 2.7.0.dev20250919__tar.gz → 2.7.0.dev20250921__tar.gz - Mend

pyg-nightly 2.7.0.dev20250919tar.gz → 2.7.0.dev20250921tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.

This version of pyg-nightly might be problematic. Click here for more details.

Files changed (660) hide show

{pyg_nightly-2.7.0.dev20250919 → pyg_nightly-2.7.0.dev20250921}/PKG-INFO RENAMED Viewed

@@ -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 → pyg_nightly-2.7.0.dev20250921}/README.md RENAMED Viewed

@@ -4,14 +4,21 @@
 ______________________________________________________________________
+<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.
@@ -334,7 +341,7 @@ 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
@@ -459,15 +466,11 @@ 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 → pyg_nightly-2.7.0.dev20250921}/pyproject.toml RENAMED Viewed

@@ -4,13 +4,13 @@ build-backend="flit_core.buildapi"
 [project]
 name="pyg-nightly"
-version="2.7.0.dev20250919"
+version="2.7.0.dev20250921"
 authors=[
     {name="Matthias Fey", email="matthias@pyg.org"},
 ]
 description="Graph Neural Network Library for PyTorch"
 readme="README.md"
-requires-python=">=3.9"
+requires-python=">=3.10"
 keywords=[
     "deep-learning",
     "pytorch",
@@ -23,7 +23,6 @@ license-files = ["LICENSE"]
 classifiers=[
     "Development Status :: 5 - Production/Stable",
     "Programming Language :: Python",
-    "Programming Language :: Python :: 3.9",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
@@ -92,7 +91,8 @@ full = [
     "numba<0.60.0",
     "opt_einsum",
     "pandas",
-    "pgmpy",
+    # See https://github.com/pgmpy/pgmpy/issues/2360.
+    # "pgmpy",
     "pynndescent",
     "pytorch-memlab",
     "rdflib",
@@ -156,7 +156,7 @@ skip = [".gitignore", "__init__.py"]
 src = ["torch_geometric"]
 line-length = 80
 indent-width = 4
-target-version = "py39"
+target-version = "py310"
 [tool.ruff.lint]
 select = [
@@ -164,6 +164,7 @@ select = [
     "D",  # pydocstyle
 ]
 ignore = [
+    "B905",  # TODO Don't ignore "zip with strict=False"
     "D100",  # TODO Don't ignore "Missing docstring in public module"
     "D101",  # TODO Don't ignore "Missing docstring in public class"
     "D102",  # TODO Don't ignore "Missing docstring in public method"
@@ -204,6 +205,8 @@ filterwarnings = [
     # Filter `pytorch_lightning` warnings:
     "ignore:GPU available but not used:UserWarning",
     "error::DeprecationWarning",
+    # TODO(rishipuri98): Remove usage of `torch_geometric.distributed` from `torch_geometric.llm`
+    "ignore:.*torch_geometric.distributed.*:DeprecationWarning",
 ]
 markers = [
     "rag: mark test as RAG test",

{pyg_nightly-2.7.0.dev20250919 → pyg_nightly-2.7.0.dev20250921}/torch_geometric/__init__.py RENAMED Viewed

@@ -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',

{pyg_nightly-2.7.0.dev20250919 → pyg_nightly-2.7.0.dev20250921}/torch_geometric/config_store.py RENAMED Viewed

@@ -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[...]`:

{pyg_nightly-2.7.0.dev20250919 → pyg_nightly-2.7.0.dev20250921}/torch_geometric/data/dataset.py RENAMED Viewed

@@ -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 "

{pyg_nightly-2.7.0.dev20250919 → pyg_nightly-2.7.0.dev20250921}/torch_geometric/datasets/molecule_gpt_dataset.py RENAMED Viewed

@@ -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.

{pyg_nightly-2.7.0.dev20250919 → pyg_nightly-2.7.0.dev20250921}/torch_geometric/datasets/tag_dataset.py RENAMED Viewed

@@ -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)

{pyg_nightly-2.7.0.dev20250919 → pyg_nightly-2.7.0.dev20250921}/torch_geometric/distributed/__init__.py RENAMED Viewed

@@ -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',

{pyg_nightly-2.7.0.dev20250919 → pyg_nightly-2.7.0.dev20250921}/torch_geometric/metrics/link_pred.py RENAMED Viewed

@@ -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)

{pyg_nightly-2.7.0.dev20250919 → pyg_nightly-2.7.0.dev20250921}/torch_geometric/nn/models/basic_gnn.py RENAMED Viewed

@@ -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

{pyg_nightly-2.7.0.dev20250919 → pyg_nightly-2.7.0.dev20250921}/torch_geometric/typing.py RENAMED Viewed

@@ -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