Research map / Architectures and efficiency / RNNs and normalization
Quasi-Equivariant Metanetworks
Viet-Hoang Tran, An Nguyen The, Benoît Guérand, Thieu Vo, Tan Minh Nguyen
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 quasi-equivariant layer to Monomial-NFN | Monomial-NFN · Small CNN Zoo ReLU (U[1,1e4] aug) | Kendall tau: 0.920 -> 0.924 | Improved |
| scale up Monomial-NFN by 68.65% params (ablation) | Monomial-NFN · Small CNN Zoo ReLU | Kendall tau: 0.922 -> 0.923 (no augment) | No clear effect |
| add quasi layer to Monomial-NFN | Monomial-NFN · INR classification MNIST | accuracy (%): 68.43 -> 70.21 | Improved |
| add quasi layer to Monomial-NFN | Monomial-NFN · INR classification CIFAR-10 | accuracy (%): 34.23 -> 35.32 | Improved |
| add ~3% params to Monomial-NFN without quasi layer (ablation) | Monomial-NFN · INR classification | accuracy (%): 34.23 -> 34.26 (CIFAR-10) | No clear effect |
| add quasi layer to Transformer-NFN | Transformer-NFN · MNIST-Transformers | Kendall tau: 0.905 -> 0.911 | Improved |
| add quasi layer to Transformer-NFN | Transformer-NFN · AGNews-Transformers | Kendall tau: 0.910 -> 0.914 | Improved |
| scale up Transformer-NFN by ~58% params (ablation) | Transformer-NFN · MNIST-Transformers | Kendall tau: 0.905 -> 0.907 | Improved |
Closest papers by meaning
- A Tale of Two Symmetries: Exploring the Loss Landscape of Equivariant Models (NeurIPS 2025 · similarity 0.90)
- Scale Equivariant Graph Metanetworks (NeurIPS 2024 · similarity 0.89)
- A Characterization Theorem for Equivariant Networks with Point-wise Activations (ICLR 2024 · similarity 0.89)
- Improving Equivariant Networks with Probabilistic Symmetry Breaking (ICLR 2025 · similarity 0.88)
- Learning (Approximately) Equivariant Networks via Constrained Optimization (NeurIPS 2025 · similarity 0.88)
- Approximately Equivariant Neural Processes (NeurIPS 2024 · similarity 0.88)
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.
