Research map / Label-efficient and robust learning / Semi-supervised learning
VIME: Extending the Success of Self- and Semi-supervised Learning to Tabular Domain
Jinsung Yoon, Yao Zhang, James Jordon, Mihaela van der Schaar
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 |
|---|---|---|---|
| VIME self+semi-supervised learning vs MixUp | 2-layer MLP predictor · Prostate Hormone | AUROC: .8448 -> .8602 | Improved |
| VIME vs MixUp | 2-layer MLP predictor · Prostate Radical | AUROC: .8214 -> .8391 | Improved |
| VIME vs MixUp | predictor · UCI Income | accuracy: .8701 -> .8804 | Improved |
| VIME vs MixUp | predictor · MNIST | accuracy: .9461 -> .9577 | Improved |
| VIME vs MixUp | predictor · UCI Blog | accuracy: .8088 -> .8389 | Improved |
| self-supervised pretraining with DAE/Context Encoder | tabular predictor · Prostate Hormone | AUROC: .8423 (XGBoost) -> .8308/.8335 | Hurt |
| add self-supervised encoder (mask+feature estimation) (ablation) | Semi-SL only VIME · UCI Blog | accuracy: .8361 -> .8389 | Improved |
| add self-supervised encoder (ablation) | Semi-SL only VIME · MNIST | accuracy: .9548 -> .9577 | Improved |
| add semi-supervised consistency loss (ablation) | Self-SL only VIME · UCI Income | accuracy: .8599 -> .8804 | Improved |
| add self-supervised encoder alone (ablation) | 2-layer MLP · UCI Blog | accuracy: .7972 -> .8147 | Improved |
| add semi-supervised consistency alone (ablation) | 2-layer MLP · UCI Income | accuracy: .8520 -> .8771 | Improved |
Later papers that compared with this method
3 later accepted papers report VIME as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- APAR: Modeling Irregular Target Functions in Tabular Regression via Arithmetic-Aware Pre-Training and Adaptive-Regularized Fine-Tuning (AAAI 2025 · better on 1 of 1 shared result)
- Towards Semi-supervised Learning with Non-random Missing Labels (ICCV 2023 · better on 1 of 1 shared result)
- TransTab: Learning Transferable Tabular Transformers Across Tables (NeurIPS 2022 · better on 1 of 1 shared result)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- CACTI: Leveraging Copy Masking and Contextual Information to Improve Tabular Data Imputation (ICML 2025 · similarity 0.88)
- ReMasker: Imputing Tabular Data with Masked Autoencoding (ICLR 2024 · similarity 0.88)
- Hybrid Autoencoders for Tabular Data: Leveraging Model-Based Augmentation in Low-Label Settings (NeurIPS 2025 · similarity 0.88)
- Representation Space Augmentation for Effective Self-Supervised Learning on Tabular Data (AAAI 2025 · similarity 0.87)
- TabDPT: Scaling Tabular Foundation Models on Real Data (NeurIPS 2025 · similarity 0.87)
- TabGLM: Tabular Graph Language Model for Learning Transferable Representations Through Multi-Modal Consistency Minimization (AAAI 2025 · similarity 0.86)
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.
