pyg-nightly 2.7.0.dev20250122__py3-none-any.whl → 2.7.0.dev20250124__py3-none-any.whl

{pyg_nightly-2.7.0.dev20250122.dist-info → pyg_nightly-2.7.0.dev20250124.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: pyg-nightly
-Version: 2.7.0.dev20250122
+Version: 2.7.0.dev20250124
 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.dev20250122.dist-info → pyg_nightly-2.7.0.dev20250124.dist-info}/RECORD

@@ -1,4 +1,4 @@
-torch_geometric/__init__.py,sha256=6uAYPnzs2ioPbhZa8-9MVViVgklvCD1v_1Vc8B9t3zI,1904
+torch_geometric/__init__.py,sha256=woO2qQnJ5h-sALP2KdvQ69AVAzlveBh2Qs87DiEu7A4,1904
 torch_geometric/_compile.py,sha256=f-WQeH4VLi5Hn9lrgztFUCSrN_FImjhQa6BxFzcYC38,1338
 torch_geometric/_onnx.py,sha256=V9ffrIKSqhDw6xUZ12lkuSfNs48cQp2EeJ6Z19GfnVw,349
 torch_geometric/backend.py,sha256=lVaf7aLoVaB3M-UcByUJ1G4T4FOK6LXAg0CF4W3E8jo,1575
@@ -54,7 +54,7 @@ torch_geometric/data/temporal.py,sha256=WOJ6gFrTLikaLhUvotyUF5ql14FkE5Ox3hNkdSp6
 torch_geometric/data/view.py,sha256=XjkVSc-UWZFCT4DlXLShZtO8duhFQkS9gq88zZXANsk,1089
 torch_geometric/data/lightning/__init__.py,sha256=w3En1tJfy3kSqe1MycpOyZpHFO3fxBCgNCUOznPA3YU,178
 torch_geometric/data/lightning/datamodule.py,sha256=Bn9iaIfE4NWDDWWMqCvBeZ4bIW1Silx_Ol5CPJCliaQ,29242
-torch_geometric/datasets/__init__.py,sha256=HYgogFHWZabd5yLfc1E4eHy9QsY6ILFRPTgfOorNwWQ,6077
+torch_geometric/datasets/__init__.py,sha256=eqVmuffZnc-O7KBdXO98SNVwSGehT5uy2LAC86MxGO4,6107
 torch_geometric/datasets/actor.py,sha256=oUxgJIX8bi5hJr1etWNYIFyVQNDDXi1nyVpHGGMEAGQ,4304
 torch_geometric/datasets/airfrans.py,sha256=212gYsk7PvF-qcmvM2YXaOBhFrS79evAGg_sPHXih4w,5439
 torch_geometric/datasets/airports.py,sha256=b3gkv3gY2JkUpmGiz36Z-g7EcnSfU8lBG1YsCOWdJ6k,3758
@@ -153,7 +153,7 @@ torch_geometric/datasets/tosca.py,sha256=nUSF8NQT1GlkwWQLshjWmr8xORsvRHzzIqhUyDC
 torch_geometric/datasets/tu_dataset.py,sha256=14OSaXBgVwT1dX2h1wZ3xVIwoo0GQBEfR3yWh6Q0VF0,7847
 torch_geometric/datasets/twitch.py,sha256=qfEerf-Uaojx2ZvegENowdG4E7RoUT_HUO9xtULadvo,3658
 torch_geometric/datasets/upfd.py,sha256=crqO8uQNz1wC1JOn4prSs8iOGv9LuLK3dZf_KUV9tUE,7010
-torch_geometric/datasets/web_qsp_dataset.py,sha256=tCVMFRT1FqlukkrdcN-qS2jYWvVYocy3-_ZeCpWwIEk,8905
+torch_geometric/datasets/web_qsp_dataset.py,sha256=7ygTK2LGRvJtnlyM3rl-9GV3VpRQWQY_ettKoJRnXz4,11120
 torch_geometric/datasets/webkb.py,sha256=beC1kWeW7cIjYwWyaINQSk-3lmVR85Lus7cKZniHp8Y,4879
 torch_geometric/datasets/wikics.py,sha256=iTzYif1WvbMXnMdhPMfvrkVaAbnM009WiB_f_JWZqhU,3879
 torch_geometric/datasets/wikidata.py,sha256=9mYShF_HlpTmcdLpiaP_tYJ9eQtUOu5vRPvohN6RXqI,4979
@@ -629,6 +629,6 @@ 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.dev20250122.dist-info/WHEEL,sha256=CpUCUxeHQbRN5UGRQHYRJorO5Af-Qy_fHMctcQ8DSGI,82
-pyg_nightly-2.7.0.dev20250122.dist-info/METADATA,sha256=JOKsGMFgqMMCa0rxpsjhLPD5bqoJ1lXrzBALYWKHWYk,62977
-pyg_nightly-2.7.0.dev20250122.dist-info/RECORD,,
+pyg_nightly-2.7.0.dev20250124.dist-info/WHEEL,sha256=CpUCUxeHQbRN5UGRQHYRJorO5Af-Qy_fHMctcQ8DSGI,82
+pyg_nightly-2.7.0.dev20250124.dist-info/METADATA,sha256=Rzd4j6F9Pjy0ArOM92QFdu_jUeoFnqyDAbIlh136kzk,62977
+pyg_nightly-2.7.0.dev20250124.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.dev20250122'
+__version__ = '2.7.0.dev20250124'
 
 __all__ = [
     'Index',

torch_geometric/datasets/__init__.py

@@ -76,7 +76,7 @@ from .wikidata import Wikidata5M
 from .myket import MyketDataset
 from .brca_tgca import BrcaTcga
 from .neurograph import NeuroGraphDataset
-from .web_qsp_dataset import WebQSPDataset
+from .web_qsp_dataset import WebQSPDataset, CWQDataset
 from .git_mol_dataset import GitMolDataset
 from .molecule_gpt_dataset import MoleculeGPTDataset
 from .tag_dataset import TAGDataset
@@ -193,6 +193,7 @@ homo_datasets = [
     'BrcaTcga',
     'NeuroGraphDataset',
     'WebQSPDataset',
+    'CWQDataset',
     'GitMolDataset',
     'MoleculeGPTDataset',
     'TAGDataset',

torch_geometric/datasets/web_qsp_dataset.py

@@ -117,12 +117,13 @@ def retrieval_via_pcst(
     return data, desc
 
 
-class WebQSPDataset(InMemoryDataset):
-    r"""The WebQuestionsSP dataset of the `"The Value of Semantic Parse
-    Labeling for Knowledge Base Question Answering"
-    <https://aclanthology.org/P16-2033/>`_ paper.
+class KGQABaseDataset(InMemoryDataset):
+    r"""Base class for the 2 KGQA datasets used in `"Reasoning on Graphs:
+    Faithful and Interpretable Large Language Model Reasoning"
+    <https://arxiv.org/pdf/2310.01061>`_ paper.
 
     Args:
+        dataset_name (str): HuggingFace `dataset` name.
         root (str): Root directory where the dataset should be saved.
         split (str, optional): If :obj:`"train"`, loads the training dataset.
             If :obj:`"val"`, loads the validation dataset.
@@ -134,11 +135,14 @@ class WebQSPDataset(InMemoryDataset):
     """
     def __init__(
         self,
+        dataset_name: str,
         root: str,
         split: str = "train",
         force_reload: bool = False,
         use_pcst: bool = True,
+        use_cwq: bool = True,
     ) -> None:
+        self.dataset_name = dataset_name
         self.use_pcst = use_pcst
         super().__init__(root, force_reload=force_reload)
 
@@ -156,7 +160,7 @@ class WebQSPDataset(InMemoryDataset):
         import datasets
         import pandas as pd
 
-        datasets = datasets.load_dataset('rmanluo/RoG-webqsp')
+        datasets = datasets.load_dataset(self.dataset_name)
 
         device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
         model_name = 'sentence-transformers/all-roberta-large-v1'
@@ -244,3 +248,45 @@ class WebQSPDataset(InMemoryDataset):
                 data_list.append(data)
 
             self.save(data_list, path)
+
+
+class WebQSPDataset(KGQABaseDataset):
+    r"""The WebQuestionsSP dataset of the `"The Value of Semantic Parse
+    Labeling for Knowledge Base Question Answering"
+    <https://aclanthology.org/P16-2033/>`_ paper.
+
+    Args:
+        root (str): Root directory where the dataset should be saved.
+        split (str, optional): If :obj:`"train"`, loads the training dataset.
+            If :obj:`"val"`, loads the validation dataset.
+            If :obj:`"test"`, loads the test dataset. (default: :obj:`"train"`)
+        force_reload (bool, optional): Whether to re-process the dataset.
+            (default: :obj:`False`)
+        use_pcst (bool, optional): Whether to preprocess the dataset's graph
+            with PCST or return the full graphs. (default: :obj:`True`)
+    """
+    def __init__(self, root: str, split: str = "train",
+                 force_reload: bool = False, use_pcst: bool = True) -> None:
+        dataset_name = 'rmanluo/RoG-webqsp'
+        super().__init__(dataset_name, root, split, force_reload, use_pcst)
+
+
+class CWQDataset(KGQABaseDataset):
+    r"""The ComplexWebQuestions (CWQ) dataset of the `"The Web as a
+    Knowledge-base forAnswering Complex Questions"
+    <https://arxiv.org/pdf/1803.06643>`_ paper.
+
+    Args:
+        root (str): Root directory where the dataset should be saved.
+        split (str, optional): If :obj:`"train"`, loads the training dataset.
+            If :obj:`"val"`, loads the validation dataset.
+            If :obj:`"test"`, loads the test dataset. (default: :obj:`"train"`)
+        force_reload (bool, optional): Whether to re-process the dataset.
+            (default: :obj:`False`)
+        use_pcst (bool, optional): Whether to preprocess the dataset's graph
+            with PCST or return the full graphs. (default: :obj:`True`)
+    """
+    def __init__(self, root: str, split: str = "train",
+                 force_reload: bool = False, use_pcst: bool = True) -> None:
+        dataset_name = 'rmanluo/RoG-cwq'
+        super().__init__(dataset_name, root, split, force_reload, use_pcst)