Research map / Architectures and efficiency / RNNs and normalization
Scalable Rule-Based Representation Learning for Interpretable Classification
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 |
|---|---|---|---|
| Use RRL instead of the strongest compared interpretable baselines | RRL · 13 datasets | F1 score (%) | Mixed |
| Train with Gradient Grafting instead of STE, ProxQuant, or random binarization (ablation) | RRL · three datasets in Figure | training loss | Helped |
| Use STE for discrete-model training (ablation) | RRL · three datasets in Figure | training loss | Hurt |
| Use ProxQuant or random binarization for discrete-model training instead of Gradient Grafting (ablation) | RRL · three datasets in Figure | training loss | Hurt |
| Replace improved logical activation functions with the original functions (ablation) | RRL (GradGrafting(NI)) · activity | training performance | Hurt |
| Replace improved logical activation functions with the original functions (ablation) | RRL (GradGrafting(NI)) · facebook | training performance | No clear effect |
Closest papers by meaning
- Learning Accurate and Interpretable Decision Rule Sets from Neural Networks (AAAI 2021 · similarity 0.86)
- Multi-value Rule Sets for Interpretable Classification with Feature-Efficient Representations (NeurIPS 2018 · similarity 0.85)
- Learning Interpretable Decision Rule Sets: A Submodular Optimization Approach (NeurIPS 2021 · similarity 0.84)
- Self-supervised Representation Learning from Random Data Projectors (ICLR 2024 · similarity 0.81)
- Non-negative Contrastive Learning (ICLR 2024 · similarity 0.81)
- Explainable Neural Networks with Guarantee: A Sparse Estimation Approach (AAAI 2025 · similarity 0.80)
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.