Research map / Probabilistic and scientific modeling / Molecules and proteins
Inverse Learning of Symmetries
Mario Wieser, Sonali Parbhoo, Aleksander Wieczorek, Volker Roth
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add adversarial mutual-information regulariser (ablation) | STIB · Artificial experiment | MI(Z0,Y) bits: 3.19 -> 0.25 | Improved |
| add adversarial regulariser (text values) (ablation) | STIB · Artificial experiment | MI(Z0,Y) bits: 3.85 -> 0.30 | Improved |
| add adversarial regulariser (ablation) | STIB · QM9 | MI(Z0,Y) bits: 0.66 -> 0.09 | Improved |
| add adversarial regulariser (ablation) | STIB · Artificial experiment | MAE(X): 0.01 -> 0.04 | Hurt |
| add adversarial regulariser (ablation) | STIB · Artificial experiment | MAE(Y): 0.65 -> 0.47 | Improved |
| add adversarial regulariser (ablation) | STIB · QM9 | SMILES reconstruction accuracy: 0.98 -> 0.98 | No clear effect |
| add adversarial regulariser (ablation) | STIB · QM9 | bandgap MAE (eV): 0.28 -> 0.27 | No clear effect |
| add adversarial regulariser (ablation) | STIB · QM9 | polarisability MAE (bohr^3): 0.70 -> 0.77 | Hurt |
| STIB instead of VAE | STIB · Artificial experiment | MI(Z0,Y) bits: 3.89 -> 0.25 | Improved |
| STIB instead of CVAE | STIB · Artificial experiment | MI(Z0,Y) bits: 2.57 -> 0.25 | Improved |
| STIB instead of CVIB | STIB · Artificial experiment | MI(Z0,Y) bits: 2.45 -> 0.25 | Improved |
| STIB instead of CVIB | STIB · QM9 | MI(Z0,Y) bits: 0.03 -> 0.09 | Hurt |
Closest papers by meaning
- Learning Infinitesimal Generators of Continuous Symmetries from Data (NeurIPS 2024 · similarity 0.89)
- A Generative Model of Symmetry Transformations (NeurIPS 2024 · similarity 0.86)
- Improving Equivariant Networks with Probabilistic Symmetry Breaking (ICLR 2025 · similarity 0.86)
- Symmetry-Informed Governing Equation Discovery (NeurIPS 2024 · similarity 0.85)
- Symmetry Discovery Beyond Affine Transformations (NeurIPS 2024 · similarity 0.85)
- Learning symmetries via weight-sharing with doubly stochastic tensors (NeurIPS 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
