Research map / Probabilistic and scientific modeling / Causal discovery
Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets
Vishnu Suresh Lokhande, Rudrasis Chakraborty, Sathya N. Ravi, Vikas Singh
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 |
|---|---|---|---|
| Use equivariant covariate representations plus site-invariant MMD training instead of Naive pooling | Pooled German dataset · German | ΔEq: 4.6{\scriptscriptstyle(0.7)} -> 6.4{\scriptscriptstyle(0.6)} | Improved |
| Use equivariant covariate representations plus site-invariant MMD training instead of Naive pooling | Pooled German dataset · German | Adv: 0.62{\scriptscriptstyle(0.03)} -> 0.54{\scriptscriptstyle(0.01)} | Improved |
| Use equivariant covariate representations plus site-invariant MMD training instead of Naive pooling | Pooled German dataset · German | ACC: 74{\scriptscriptstyle(0.9)} -> 75{\scriptscriptstyle(3.3)} | No clear effect |
| Use equivariant covariate representations plus site-invariant MMD training instead of Naive pooling | Pooled Adult dataset · Adult | ΔEq: 3.4{\scriptscriptstyle(0.7)} -> 5.3{\scriptscriptstyle(0.9)} | Improved |
| Use equivariant covariate representations plus site-invariant MMD training instead of Naive pooling | Pooled Adult dataset · Adult | Adv: 83{\scriptscriptstyle(0.1)} -> 75{\scriptscriptstyle(1.4)} | Improved |
| Use equivariant covariate representations plus site-invariant MMD training instead of Naive pooling | Pooled Adult dataset · Adult | ACC: 84{\scriptscriptstyle(0.1)} -> 83{\scriptscriptstyle(0.1)} | No clear effect |
| Use equivariant covariate representations plus site-invariant MMD training instead of Naive pooling | Pooled ADNI dataset · ADNI | ΔEq: 3.1{\scriptscriptstyle(1.0)} -> 5.1{\scriptscriptstyle(1.2)} | Improved |
| Use equivariant covariate representations plus site-invariant MMD training instead of Naive pooling | Pooled ADNI dataset · ADNI | MMD: 27{\scriptscriptstyle(1.6)} -> 16{\scriptscriptstyle(7.2)} | Improved |
| Use equivariant covariate representations plus site-invariant MMD training instead of Naive pooling | Pooled ADNI dataset · ADNI | ACC: 80{\scriptscriptstyle(2.6)} -> 77{\scriptscriptstyle(4.8)} | Hurt |
| Use equivariant covariate representations plus site-invariant MMD training instead of Naive pooling | Pooled ADCP dataset · ADCP | ΔEq: 4.1{\scriptscriptstyle(0.9)} -> 7.5{\scriptscriptstyle(1.2)} | Improved |
| Use equivariant covariate representations plus site-invariant MMD training instead of Naive pooling | Pooled ADCP dataset · ADCP | MMD: 90{\scriptscriptstyle(8.7)} -> 70{\scriptscriptstyle(22.3)} | Improved |
| Use equivariant covariate representations plus site-invariant MMD training instead of Naive pooling | Pooled ADCP dataset · ADCP | ACC: 83{\scriptscriptstyle(4.4)} -> 81{\scriptscriptstyle(1.8)} | Hurt |
Closest papers by meaning
- Pooling Image Datasets with Multiple Covariate Shift and Imbalance (ICLR 2024 · similarity 0.87)
- CASL-VAE: Learning Structured Latent Variables from Unpaired Data for Semi-supervised Clustering and Paired Sample Generation (NeurIPS 2026 · similarity 0.84)
- A Tale of Two Symmetries: Exploring the Loss Landscape of Equivariant Models (NeurIPS 2025 · similarity 0.84)
- Pooling Versus Ensembling for Ridge Regression Under Covariate Shift (NeurIPS 2026 · similarity 0.84)
- Causal Representation Learning from Multimodal Biomedical Observations (ICLR 2025 · similarity 0.84)
- Unifying Causal Representation Learning with the Invariance Principle (ICLR 2025 · 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.
