Skip to content

Drop torch.jit.script from SelectOutput and ConnectOutput #10701

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

Open
V-3604 wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Drop torch.jit.script from SelectOutput and ConnectOutput #10701

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3d5118e
Drop torch.jit.script from SelectOutput and ConnectOutput
V-3604 May 19, 2026
62d767a
Merge branch 'master' into fix/jit-script-pool-outputs
akihironitta Jun 3, 2026
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
1 change: 1 addition & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).

### Fixed

- Removed `torch.jit.script` calls on `SelectOutput` and `ConnectOutput` to avoid `DeprecationWarning` on PyTorch 2.12 ([#10697](https://github.com/pyg-team/pytorch_geometric/issues/10697))
- Fix MovieLens dataset incompatibility with `sentence-transformers>=5.0.0` ([#10668](https://github.com/pyg-team/pytorch_geometric/pull/10668)
- Removed an unnecessary device synchronization in `torch_geometric.utils.softmax` ([#10499](https://github.com/pyg-team/pytorch_geometric/pull/10499))
- Fixed loading of legacy HuggingFace BERT checkpoints ([#10631](https://github.com/pyg-team/pytorch_geometric/pull/10631))
Expand Down
9 changes: 2 additions & 7 deletions torch_geometric/nn/pool/connect/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,3 @@
from dataclasses import dataclass
from typing import Optional

import torch
Expand All @@ -7,7 +6,6 @@
from torch_geometric.nn.pool.select import SelectOutput


@dataclass(init=False)
class ConnectOutput:
r"""The output of the :class:`Connect` method, which holds the coarsened
graph structure, and optional pooled edge features and batch vectors.
Expand All @@ -20,8 +18,8 @@ class ConnectOutput:
coarsened graph. (default: :obj:`None`)
"""
edge_index: Tensor
edge_attr: Optional[Tensor] = None
batch: Optional[Tensor] = None
edge_attr: Optional[Tensor]
batch: Optional[Tensor]

def __init__(
self,
Expand All @@ -48,9 +46,6 @@ def __init__(
self.batch = batch


ConnectOutput = torch.jit.script(ConnectOutput)


class Connect(torch.nn.Module):
r"""An abstract base class for implementing custom edge connection
operators as described in the `"Understanding Pooling in Graph Neural
Expand Down
7 changes: 1 addition & 6 deletions torch_geometric/nn/pool/select/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,11 +1,9 @@
from dataclasses import dataclass
from typing import Optional

import torch
from torch import Tensor


@dataclass(init=False)
class SelectOutput:
r"""The output of the :class:`Select` method, which holds an assignment
from selected nodes to their respective cluster(s).
Expand All @@ -23,7 +21,7 @@ class SelectOutput:
num_nodes: int
cluster_index: Tensor
num_clusters: int
weight: Optional[Tensor] = None
weight: Optional[Tensor]

def __init__(
self,
Expand Down Expand Up @@ -62,9 +60,6 @@ def __init__(
self.weight = weight


SelectOutput = torch.jit.script(SelectOutput)


class Select(torch.nn.Module):
r"""An abstract base class for implementing custom node selections as
described in the `"Understanding Pooling in Graph Neural Networks"
Expand Down
Loading