Track: Track2; Team name: CtrlAltMe; Model: SMCN

[Salwa08]

Summary

This PR submits SMCN (Scalable Multi-Cellular Networks) for the 2026 TDL Challenge Track 2.

Submission

• Track: Track 2
• Team name: CtrlAltMe
• Model: SMCN
• Model config: configs/model/combinatorial/smcn.yaml
• Results file: 2026_tdl_challenge/outputs/2026-07-20_23-26-18_merged/results.json

Reference

SMCN is introduced in:

Yam Eitan, Yoav Gelberg, Guy Bar-Shalom, Fabrizio Frasca, Michael Bronstein, and Haggai Maron.
Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity.
arXiv:2408.05486, 2024.
https://arxiv.org/abs/2408.05486

Implementation

• Adds an SMCN combinatorial backbone in topobench/nn/backbones/combinatorial/smcn.py.
• Builds rank-0/2 incident tuple features from combinatorial batch incidences.
• Adds bridge-aware tuple edges and relation-specific subcomplex message passing.
• Pools tuple features back to rank-0 and rank-2 cells.
• Reuses AllCellFeatureEncoder, TuneWrapper, and PropagateSignalDown.

Validation

• pytest test/nn/backbones/combinatorial/test_smcn.py -q -p no:cacheprovider
• ruff check topobench/nn/backbones/combinatorial/smcn.py test/nn/backbones/combinatorial/test_smcn.py
• Challenge grid completed: 72/72 runs
• Results file contains 72 rows

[Copilot]

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.

[Salwa08]

Hi maintainers, this is a Track 2 TNN submission. Could you please add the track-2-tnn label? I don't have permission to apply repository labels. Thank you!