Skip to content

Update movie_lens.py to use pyg SentenceTransformer #10493

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 5 commits into
base: master
Choose a base branch
from
Draft

Update movie_lens.py to use pyg SentenceTransformer #10493

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
8296a44
Update movie_lens.py to use pyg sentence transformer
puririshi98 Oct 9, 2025
ea75e1e
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Oct 9, 2025
83fcd6a
Update movie_lens.py
puririshi98 Oct 9, 2025
c47a777
Update recommender_system.py
puririshi98 Oct 9, 2025
d69e2be
Update movie_lens.py
puririshi98 Oct 9, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion examples/hetero/recommender_system.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

path = osp.join(osp.dirname(osp.realpath(__file__)), '../../data/MovieLens')
data = MovieLens(path, model_name='all-MiniLM-L6-v2')[0]
data = MovieLens(path)[0]

# Add user node features for message passing:
data['user'].x = torch.eye(data['user'].num_nodes)
Expand Down
12 changes: 7 additions & 5 deletions torch_geometric/datasets/movie_lens.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@ def __init__(
root: str,
transform: Optional[Callable] = None,
pre_transform: Optional[Callable] = None,
model_name: Optional[str] = 'all-MiniLM-L6-v2',
model_name: Optional[str] = 'Alibaba-NLP/gte-modernbert-base',
force_reload: bool = False,
) -> None:
self.model_name = model_name
Expand All @@ -68,7 +68,8 @@ def download(self) -> None:

def process(self) -> None:
import pandas as pd
from sentence_transformers import SentenceTransformer

from torch_geometric.llm.models import SentenceTransformer

data = HeteroData()

Expand All @@ -78,10 +79,11 @@ def process(self) -> None:
genres = df['genres'].str.get_dummies('|').values
genres = torch.from_numpy(genres).to(torch.float)

model = SentenceTransformer(self.model_name)
model = SentenceTransformer(model_name=self.model_name)
if torch.cuda.is_available():
model = model.cuda()
with torch.no_grad():
emb = model.encode(df['title'].values, show_progress_bar=True,
convert_to_tensor=True).cpu()
emb = model.encode(text=df['title'].values).cpu()

data['movie'].x = torch.cat([emb, genres], dim=-1)

Expand Down
Loading