Research map / Label-efficient and robust learning / Self-supervised and contrastive
TabularBERT: Binning-Based Self-Supervised Learning for Tabular Representation
Beomjin Park, Seunghwan An, Sungchul Hong, Hosik Choi
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 SWD (Wasserstein) pretraining objective instead of CE (ablation) | TabularBERT · AD | accuracy: 0.858 -> 0.862 | Improved |
| add SWD (Wasserstein) pretraining objective instead of CE (ablation) | TabularBERT · GE | accuracy: 0.715 -> 0.733 | Improved |
| add SWD (Wasserstein) pretraining objective instead of CE (ablation) | TabularBERT · EY | accuracy: 0.787 -> 0.831 | Improved |
| add SWD (Wasserstein) pretraining objective instead of CE (ablation) | TabularBERT · CA | RMSE: 0.440 -> 0.441 | No clear effect |
| add SWD (Wasserstein) pretraining objective instead of CE (ablation) | TabularBERT · HO | RMSE: 3.149 -> 3.113 | Improved |
| add auxiliary reconstruction loss in pretraining (ablation) | TabularBERT · AD | accuracy: 0.860 -> 0.862 | Improved |
| add auxiliary reconstruction loss in pretraining (ablation) | TabularBERT · GE | accuracy: 0.716 -> 0.733 | Improved |
| add auxiliary reconstruction loss in pretraining (ablation) | TabularBERT · EY | accuracy: 0.796 -> 0.831 | Improved |
| add auxiliary reconstruction loss in pretraining (ablation) | TabularBERT · CA | RMSE: 0.440 -> 0.441 | No clear effect |
| add auxiliary reconstruction loss in pretraining (ablation) | TabularBERT · HO | RMSE: 3.151 -> 3.113 | Improved |
| increase regularization level together with many bins (ablation) | TabularBERT · CH/GE/HO | accuracy/RMSE | Improved |
| use strong fused-type regularization with few bins (ablation) | TabularBERT · CH/GE/HO | accuracy/RMSE | Hurt |
Closest papers by meaning
- Hybrid Autoencoders for Tabular Data: Leveraging Model-Based Augmentation in Low-Label Settings (NeurIPS 2025 · similarity 0.88)
- Large Scale Transfer Learning for Tabular Data via Language Modeling (NeurIPS 2024 · similarity 0.88)
- Representation Space Augmentation for Effective Self-Supervised Learning on Tabular Data (AAAI 2025 · similarity 0.88)
- TabGLM: Tabular Graph Language Model for Learning Transferable Representations Through Multi-Modal Consistency Minimization (AAAI 2025 · similarity 0.88)
- Making Pre-trained Language Models Great on Tabular Prediction (ICLR 2024 · similarity 0.87)
- STRABLE: Benchmarking Tabular Machine Learning with Strings (NeurIPS 2026 · similarity 0.87)
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.
