Research map / Architectures and efficiency / RNNs and normalization
Permutation Equivariant Neural Functionals
Allan Zhou, Kaien Yang, Kaylee Burns, Adriano Cardace, Yiding Jiang, Samuel Sokota, J Zico Kolter, Chelsea Finn
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 |
|---|---|---|---|
| Encode neuron permutation equivariance in the neural functional architecture instead of using statistical weight features | CNN generalization prediction · Small CNN Zoo: CIFAR-10-GS and SVHN-GS | Kendall's τ: 0.915 ± 0.002 -> 0.934 ± 0.001; 0.843 ± 0.000 -> 0.931 ± 0.005 | Improved |
| Use NFN_NP rather than NFN_HNP | INR classification · CIFAR-10, MNIST-10, FashionMNIST, ShapeNet-10, and ScanNet-10 | test accuracy (%): 44.1 ± 0.471 -> 46.6 ± 0.072; 92.5 ± 0.071 -> 92.9 ± 0.218; 72.7±1.53 -> 75.6±1.07; 86.9±0.860 -> 88.7±0.461; 64.1±0.572 | Mixed |
| Use permutation-equivariant NFNs instead of permutation-augmented MLPs | INR classification · CIFAR-10, MNIST-10, FashionMNIST, ShapeNet-10, and ScanNet-10 | test accuracy (%): 18.9 ± 0.432 -> 46.6 ± 0.072; 21.0 ± 0.172 -> 92.9 ± 0.218; 15.9±0.181 -> 75.6±1.07; 39.1 ± 0.385 -> 88.7±0.461; 45.5±0. | Improved |
| Predict winning-ticket masks from initialization with NFN_NP | MLP and CNN ticket prediction · MNIST and CIFAR-10 | test accuracy (%) after training with a 95% sparsity mask: 44.0±0.06 -> 41.4±0.08; 96.2±0.04 -> 94.8±0.01 | Hurt |
| Replace NFN_NP's interaction-aware layer with a pointwise layer that ignores weight interactions (ablation) | Winning-ticket mask prediction · CIFAR-10 and MNIST | test accuracy (%) after training with a 95% sparsity mask: 41.4±0.08 -> 42.6±0.07; 94.8±0.01 -> 95.0±0.01 | No clear effect |
| Remove interactions between weights and layers using a pointwise NF-Layer (ablation) | INR weight-space editing · Dilate (MNIST) and Contrast (CIFAR-10) | test mean squared error | Hurt |
Closest papers by meaning
- Universal Neural Functionals (NeurIPS 2024 · similarity 0.93)
- Equivariant Polynomial Functional Networks (ICML 2025 · similarity 0.90)
- Permutation Equivariant Neural Networks for Symmetric Tensors (ICML 2025 · similarity 0.89)
- Monomial Matrix Group Equivariant Neural Functional Networks (NeurIPS 2024 · similarity 0.89)
- Scale Equivariant Graph Metanetworks (NeurIPS 2024 · similarity 0.89)
- A Characterization Theorem for Equivariant Networks with Point-wise Activations (ICLR 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.
