Research map / Probabilistic and scientific modeling / Molecules and proteins
Group Equivariant Conditional Neural Processes
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use translation-equivariant EquivCNP instead of ConvCNP | Conditional neural processes · 1D synthetic regression, RBF | log-likelihood: 1.3271 ± 1.0324 -> 1.2930 ± 1.0113 | No clear effect |
| Use translation-equivariant EquivCNP instead of ConvCNP | Conditional neural processes · 1D synthetic regression, Matern | log-likelihood: 0.8189± 0.9366 -> 0.6616 ± 0.6728 | No clear effect |
| Use translation-equivariant EquivCNP instead of ConvCNP | Conditional neural processes · 1D synthetic regression, Periodic | log-likelihood: -0.4787 ± 0.5448 -> -0.4037 ± 0.4968 | No clear effect |
| Use rotation-scale equivariance (R_{>0} × SO(2)) | EquivCNP · Digital clock digit image completion | log-likelihood | Helped |
| Use rotation-only equivariance (SO(2)) rather than rotation-scale equivariance | EquivCNP · Digital clock digit image completion with scaled test images | log-likelihood | Hurt |
| Use rotation-only equivariance (SO(2)) rather than translation equivariance (T(2)) | EquivCNP · Digital clock digit image completion | log-likelihood | Hurt |
| Use translation-and-rotation equivariance (SE(2)) rather than translation equivariance (T(2)) | EquivCNP · Digital clock digit image completion | log-likelihood | No clear effect |
Closest papers by meaning
- Lie Group Decompositions for Equivariant Neural Networks (ICLR 2024 · similarity 0.91)
- Approximately Equivariant Neural Processes (NeurIPS 2024 · similarity 0.90)
- Variational Partial Group Convolutions for Input-Aware Partial Equivariance of Rotations and Color-Shifts (ICML 2024 · similarity 0.90)
- Probing Equivariance and Symmetry Breaking in Convolutional Networks (NeurIPS 2025 · similarity 0.90)
- A Tale of Two Symmetries: Exploring the Loss Landscape of Equivariant Models (NeurIPS 2025 · similarity 0.90)
- Neural Fourier Transform: A General Approach to Equivariant Representation Learning (ICLR 2024 · similarity 0.89)
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.