Track: Track 2; Team: E(n)igma; Model: ETNN

[grvkhnl]

Track

Track 2 — Topological Neural Networks

Team Name

E(n)igma

Model

E(n)-Equivariant Topological Neural Networks (ETNN)

Status

Draft / work in progress

Summary

This draft PR develops a TopoBench-native implementation of E(n)-Equivariant Topological Neural Networks (ETNN) for the 2026 TDL Challenge.

The implementation targets the combinatorial-complex setting and aims to integrate ETNN with the standard TopoBench configuration, training, testing, and GraphUniverse evaluation workflow.

Planned implementation

• Add ETNN backbone under the combinatorial-complex domain.
• Add Hydra model configuration.
• Implement TopoBench-compatible cell-relation message passing.
• Add required wrapper/encoder components if needed.
• Keep outputs compatible with standard TopoBench readout where possible.
• Add unit tests and forward-pass shape tests.
• Add pipeline smoke test.
• Run the official GraphUniverse evaluation notebook.
• Add generated results.json.

Design assumptions

The implementation will follow TopoBench interfaces and use the combinatorial-complex topology produced by the preprocessing/lifting pipeline. Any ETNN-specific adaptations needed for the GraphUniverse setting will be documented in the final submission.

Reference

C. Battiloro, E. Karaismailoglu, M. Tec, G. Dasoulas, M. Audirac, and F. Dominici, “E(n) Equivariant Topological Neural Networks,” in International Conference on Learning Representations (ICLR), 2025.

Paper: https://arxiv.org/abs/2405.15429

Official implementation: https://github.com/NSAPH-Projects/topological-equivariant-networks