Research map / Architectures and efficiency / CNN design
A General Framework For Proving The Equivariant Strong Lottery Ticket Hypothesis
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 |
|---|---|---|---|
| pruning overparametrized G-equivariant networks (C=5) to match trained targets | MPGNN, k-order GNN, E(2)-steerable CNN · Cora, CiteSeer, Proteins, NCI1, Rot-MNIST, FlipRot-MNIST | test accuracy | No clear effect |
| increasing overparametrization constant C from 1 to 5 (ablation) | E(2)-steerable CNNs (C4, C8, D4) · ablation over C in {1,2,5,10} | max relative output error | Helped |
| increasing overparametrization constant C from 1 to 5 (ablation) | E(2)-steerable CNNs (C4, C8, D4) · ablation over C in {1,2,5,10} | pruned accuracy: marginal | Helped |
| use equivariant-basis-based pruning with identity element in basis (ours basis vs default basis) | E(2)-steerable CNN · Rot-MNIST | test accuracy: 97.7 vs 96.2 (C4); 98.1 vs 96.8 (C8) | No clear effect |
Closest papers by meaning
- Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets (NeurIPS 2023 · similarity 0.92)
- Proving the Lottery Ticket Hypothesis for Convolutional Neural Networks (ICLR 2022 · similarity 0.91)
- Optimal Lottery Tickets via Subset Sum: Logarithmic Over-Parameterization is Sufficient (NeurIPS 2020 · similarity 0.91)
- The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks (ICLR 2019 · similarity 0.91)
- On the Sparsity of the Strong Lottery Ticket Hypothesis (NeurIPS 2024 · similarity 0.91)
- Weisfeiler and Leman Go Gambling: Why Expressive Lottery Tickets Win (ICML 2025 · similarity 0.89)
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.