Research map / Architectures and efficiency / RNNs and normalization
Regularization Learning Networks: Deep Learning for Tabular Datasets
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 RLN instead of a classical DNN regularization scheme | DNNs on microbiome trait prediction · Microbiome traits | explained variance (R²): 2.57±0.05 | Helped |
| Ensemble RLN with GBT | Microbiome trait prediction · Age, BMI, and HDL cholesterol | explained variance (R²) | Helped |
| Use RLN + GBT instead of GBT alone | Microbiome trait prediction · HDL cholesterol, Median glucose, and CRP | explained variance (R²) | Helped |
| Remove covariates from the input data (ablation) | RLN and GBT ensembles · Microbiome traits | explained variance (R²): 9%±2% -> 2%±1% | Hurt |
| Add individual, learned regularization coefficients and optimize them with Counterfactual Loss | DNNs · Microbiome trait prediction | explained variance (R²): 15%±1% less -> 2%±2% less | Helped |
Closest papers by meaning
- TabR: Tabular Deep Learning Meets Nearest Neighbors (ICLR 2024 · similarity 0.87)
- TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks (NeurIPS 2024 · similarity 0.86)
- TabArena: A Living Benchmark for Machine Learning on Tabular Data (NeurIPS 2025 · similarity 0.86)
- Retrieval & Fine-Tuning for In-Context Tabular Models (NeurIPS 2024 · similarity 0.85)
- Hybrid Autoencoders for Tabular Data: Leveraging Model-Based Augmentation in Low-Label Settings (NeurIPS 2025 · similarity 0.85)
- TabM: Advancing tabular deep learning with parameter-efficient ensembling (ICLR 2025 · similarity 0.85)
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.