Research map / Learning theory and algorithms / Sample complexity
On Universal Equivariant Set Networks
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 |
|---|---|---|---|
| Add a single linear transmission layer to PointNet (PointNetST) (ablation) | PointNet · Knapsack classification | classification success rate | Helped |
| Add a single linear transmission layer to PointNet (PointNetST) (ablation) | PointNet · Squared norm regression | regression performance | Helped |
| Add a single linear transmission layer to PointNet (PointNetST) (ablation) | PointNet · Fiedler eigenvector regression | regression performance | Helped |
| Use an equivariant universal architecture instead of a same-width non-equivariant MLP | MLP baseline · Knapsack classification | test performance | Helped |
| Use an equivariant universal architecture instead of a same-width non-equivariant MLP | MLP baseline · Squared norm regression | test performance | Helped |
| Use DeepSets instead of GraphNet | GraphNet · Knapsack classification, squared norm regression, and Fiedler eigenvector regression | task performance | Helped |
| Use a 2-layer DeepSets model to approximate a graph convolution layer | DeepSets · Graph convolution layer approximation | smooth L1 error: ~0.01 | Helped |
Closest papers by meaning
- On Universality Classes of Equivariant Networks (NeurIPS 2025 · similarity 0.89)
- A Characterization Theorem for Equivariant Networks with Point-wise Activations (ICLR 2024 · similarity 0.89)
- Universally Invariant Learning in Equivariant GNNs (NeurIPS 2025 · similarity 0.87)
- Weisfeiler Leman for Euclidean Equivariant Machine Learning (ICML 2024 · similarity 0.87)
- Universal Neural Functionals (NeurIPS 2024 · similarity 0.86)
- Deep Ridgelet Transform and Unified Universality Theorem for Deep and Shallow Joint-Group-Equivariant Machines (ICML 2025 · similarity 0.86)
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.