Research map / Architectures and efficiency / RNNs and normalization
Weight Predictor Network with Feature Selection for Small Sample Tabular Biomedical Data
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 |
|---|---|---|---|
| Replace direct first-layer weight learning with WPN-predicted weights and SPN feature gates | MLP on biomedical datasets · 9 biomedical datasets | average rank: 2.66 vs 4.44 | Helped |
| Add SPN while setting the sparsity loss to zero (ablation) | WPFS · 9 biomedical datasets | balanced accuracy | Helped |
| Add sparsity loss, using a tuned λ (ablation) | WPFS with WPN and SPN · 9 biomedical datasets | balanced accuracy | Mixed |
| Use NMF embeddings instead of feature-values or dot-histogram embeddings (ablation) | WPFS without SPN · 9 biomedical datasets | balanced accuracy: 81,28 ± 9,93 vs 73,82 ± 12,98 (average) | Helped |
| Increase the NMF embedding size from 20 to 50 (ablation) | WPFS · 9 biomedical datasets | validation weighted cross-entropy: 0,3267 ± 0,1377 -> 0,3083 ± 0,1436 (Average) | Mixed |
| Use WPN to generate the first-layer weights (ablation) | WPFS · 9 biomedical datasets | balanced accuracy | Mixed |
| Increase λ to encourage stronger feature sparsity (ablation) | WPFS · 9 biomedical datasets | proportion of selected features: ∼ 25% to ∼ 0.1 - 1% | Hurt |
| Use WPFS instead of an MLP (ablation) | MLP · metabric-dr with very few samples | balanced accuracy | Helped |
Closest papers by meaning
- ProtoGate: Prototype-based Neural Networks with Global-to-local Feature Selection for Tabular Biomedical Data (ICML 2024 · similarity 0.86)
- TabPFN Unleashed: A Scalable and Effective Solution to Tabular Classification Problems (ICML 2025 · similarity 0.85)
- SAND: One-Shot Feature Selection with Additive Noise Distortion (ICML 2025 · similarity 0.84)
- Latent Score-Based Reweighting for Robust Classification on Imbalanced Tabular Data (ICML 2025 · similarity 0.83)
- A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilities (NeurIPS 2025 · similarity 0.83)
- TabFlex: Scaling Tabular Learning to Millions with Linear Attention (ICML 2025 · similarity 0.82)
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.