Skip to content

Track: Track2; Team name: One Ring to Lift Them All; Model: DiffLift-SMCN #406

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
JorgeLuizFranco wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Track: Track2; Team name: One Ring to Lift Them All; Model: DiffLift-SMCN #406

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
6d06b66
Add SMCN cell model with learnable two-cell selection (Track 2)
Jul 18, 2026
493659a
Move DiffLift into topobench/nn/liftings as a standalone learnable li…
Jul 30, 2026
1530279
Add challenge evaluation results (72-run GraphUniverse grid)
Jul 30, 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
5,272 changes: 5,272 additions & 0 deletions 2026_tdl_challenge/outputs/2026-07-27_05-00-00/results.json
View file
Open in desktop

Large diffs are not rendered by default.

41 changes: 41 additions & 0 deletions configs/model/cell/smcn.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,41 @@
_target_: topobench.model.TBModel

model_name: smcn
model_domain: cell

feature_encoder:
_target_: topobench.nn.encoders.${model.feature_encoder.encoder_name}
encoder_name: AllCellFeatureEncoder
in_channels: ${infer_in_channels:${dataset},${oc.select:transforms,null}}
out_channels: 64
proj_dropout: 0.0

backbone:
_target_: topobench.nn.backbones.cell.smcn.SMCN
in_channels: ${model.feature_encoder.out_channels}
sub_channels: 32
n_cin_layers: 1
n_scl_layers: 3
num_mlp_layers: 2
max_rank_out: 1
max_dist: 10
dropout: 0.0

backbone_wrapper:
_target_: topobench.nn.wrappers.SMCNWrapper
_partial_: true
wrapper_name: SMCNWrapper
out_channels: ${model.feature_encoder.out_channels}
num_cell_dimensions: ${infer_num_cell_dimensions:${oc.select:model.feature_encoder.selected_dimensions,null},${model.feature_encoder.in_channels}}

readout:
_target_: topobench.nn.readouts.${model.readout.readout_name}
readout_name: PropagateSignalDown
num_cell_dimensions: ${infer_num_cell_dimensions:${oc.select:model.feature_encoder.selected_dimensions,null},${model.feature_encoder.in_channels}}
hidden_dim: ${model.feature_encoder.out_channels}
out_channels: ${dataset.parameters.num_classes}
task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}}
pooling_type: sum

# compile model for faster training with pytorch 2.0
compile: false
43 changes: 43 additions & 0 deletions configs/model/cell/smcn_difflift.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,43 @@
_target_: topobench.model.TBModel

model_name: smcn_difflift
model_domain: cell

feature_encoder:
_target_: topobench.nn.encoders.${model.feature_encoder.encoder_name}
encoder_name: AllCellFeatureEncoder
in_channels: ${infer_in_channels:${dataset},${oc.select:transforms,null}}
out_channels: 64
proj_dropout: 0.0

backbone:
_target_: topobench.nn.backbones.cell.smcn.SMCN
in_channels: ${model.feature_encoder.out_channels}
sub_channels: 32
n_cin_layers: 1
n_scl_layers: 3
num_mlp_layers: 2
max_rank_out: 1
max_dist: 10
dropout: 0.0
learned_lifting: true # 2-cells selected end-to-end (DiffLift)
sharpening: 10.0

backbone_wrapper:
_target_: topobench.nn.wrappers.SMCNWrapper
_partial_: true
wrapper_name: SMCNWrapper
out_channels: ${model.feature_encoder.out_channels}
num_cell_dimensions: ${infer_num_cell_dimensions:${oc.select:model.feature_encoder.selected_dimensions,null},${model.feature_encoder.in_channels}}

readout:
_target_: topobench.nn.readouts.${model.readout.readout_name}
readout_name: PropagateSignalDown
num_cell_dimensions: ${infer_num_cell_dimensions:${oc.select:model.feature_encoder.selected_dimensions,null},${model.feature_encoder.in_channels}}
hidden_dim: ${model.feature_encoder.out_channels}
out_channels: ${dataset.parameters.num_classes}
task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}}
pooling_type: sum

# compile model for faster training with pytorch 2.0
compile: false
Loading
Loading