Research map / Probabilistic and scientific modeling / Variational and generative sampling
Improving Relational Regularized Autoencoders with Spherical Sliced Fused Gromov Wasserstein
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 |
|---|---|---|---|
| Replace SFG with SSFG | DRAE · MNIST | FID: 58.04 ± 20.74 -> 47.97 ± 13.83 | Helped |
| Replace SFG with PSSFG | DRAE · MNIST | FID: 58.04 ± 20.74 -> 49.15 ± 12.93 | Helped |
| Replace SFG with MSSFG | DRAE · MNIST | FID: 58.04 ± 20.74 -> 43.57 ± 10.98 | Helped |
| Replace SFG with SSFG | DRAE · MNIST | Reconstruction: 14.07 ± 4.31 -> 11.17 ±1.73 | Helped |
| Replace SFG with PSSFG | DRAE · MNIST | Reconstruction: 14.07 ± 4.31 -> 11.71 ±1.21 | Helped |
| Replace SFG with MSSFG | DRAE · MNIST | Reconstruction: 14.07 ± 4.31 -> 11.12 ±0.91 | Helped |
| Replace SFG with SSFG | DRAE · CelebA | FID: 50.09 ±1.33 -> 46.63 ±0.83 | Helped |
| Replace SFG with PSSFG | DRAE · CelebA | FID: 50.09 ±1.33 -> 48.21 ±1.02 | Helped |
| Replace SFG with MSSFG | DRAE · CelebA | FID: 50.09 ±1.33 -> 46.01 ±0.91 | Helped |
| Replace SFG with SSFG | DRAE · CelebA | Reconstruction: 66.05 ± 2.56 -> 66.62 ± 0.51 | Hurt |
| Replace SFG with PSSFG | DRAE · CelebA | Reconstruction: 66.05 ± 2.56 -> 66.31 ± 0.43 | Helped |
| Replace SFG with MSSFG | DRAE · CelebA | Reconstruction: 66.05 ± 2.56 -> 65.91± 0.4 | Helped |
Closest papers by meaning
- A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data (ICLR 2024 · similarity 0.85)
- Improved Baselines with Representation Autoencoders (NeurIPS 2026 · similarity 0.84)
- Sparse Autoencoders, Again? (ICML 2025 · similarity 0.84)
- Distributional Autoencoders Know the Score (NeurIPS 2025 · similarity 0.84)
- Fourier Sliced-Wasserstein Embedding for Multisets and Measures (ICLR 2025 · similarity 0.84)
- Graph Geometry-Preserving Autoencoders (ICML 2024 · similarity 0.84)
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.