Research map / Probabilistic and scientific modeling / Molecules and proteins
Learning Disentangled Representations and Group Structure of Dynamical Environments
Robin Quessard, Thomas Barrett, William Clements
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 entanglement regularisation to the loss (ablation) | group-structure method · Flatland p=10 | entanglement loss L_ent: 0.32 -> 1.2 × 10−4 | Improved |
| add entanglement regularisation (ablation) | group-structure method · Flatland multi-step prediction | reconstruction error | Improved |
| use group-structured spherical latent vs direct prediction model | group-structure method · Flatland multi-step prediction | reconstruction error | Improved |
| use latent dimension n>4 | group-structure method · Flatland | learned representation dimensionality | No clear effect |
| use one-hot observations instead of pixels | group-structure method vs VAEs · Flatland one-hot | structure recovered | Improved |
Closest papers by meaning
- Symmetry-Based Disentangled Representation Learning requires Interaction with Environments (NeurIPS 2019 · similarity 0.91)
- Disentangled representation learning through unsupervised symmetry group discovery (ICLR 2026 · similarity 0.90)
- Disentangled Representation Learning in Non-Markovian Causal Systems (NeurIPS 2024 · similarity 0.86)
- Disentangled Representation Learning with the Gromov-Monge Gap (ICLR 2025 · similarity 0.85)
- Disentangling Representations through Multi-task Learning (ICLR 2025 · similarity 0.85)
- Discovering Symmetry Breaking in Physical Systems with Relaxed Group Convolution (ICML 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.
