# SeBA: Semi-supervised few-shot learning via Separated-at-Birth Alignment for tabular data

arXiv: https://arxiv.org/abs/2605.08519 · HTML: https://mlsanity.com/paper/2605.08519/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 41 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 12 of 12)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training](https://mlsanity.com/paper/2106.01342/) (2021)
- [OpenML Benchmarking Suites](https://mlsanity.com/paper/1708.03731/) (2017)
- [Noisy Channel Language Model Prompting for Few-Shot Text Classification](https://mlsanity.com/paper/2108.04106/) (2021)
- [SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption](https://mlsanity.com/paper/2106.15147/) (2021)
- [Sequential Deep Learning for Credit Risk Monitoring with Tabular Financial Data](https://mlsanity.com/paper/2012.15330/) (2020)
- [UniTabE: A Universal Pretraining Protocol for Tabular Foundation Model in Data Science](https://mlsanity.com/paper/2307.09249/) (2023)
- [PTaRL: Prototype-based Tabular Representation Learning via Space Calibration](https://mlsanity.com/paper/2407.05364/) (2024)
- [Fine-tuned In-Context Learning Transformers are Excellent Tabular Data Classifiers](https://mlsanity.com/paper/2405.13396/) (2024)
- [HyperMAML: Few-Shot Adaptation of Deep Models with Hypernetworks](https://mlsanity.com/paper/2205.15745/) (2022)
- [Self-supervised Representation Learning From Random Data Projectors](https://mlsanity.com/paper/2310.07756/) (2023)

## Abstract (arXiv)

Learning from scarce labeled data with a larger pool of unlabeled samples, known as semi-supervised few-shot learning (SS-FSL), remains critical for applications involving tabular data in domains like medicine, finance, and science. The existing SS-FSL methods often rely on self-supervised learning (SSL) frameworks developed for vision or language, which assume the availability of a natural form of data augmentations. For tabular data, defining meaningful augmentations is non-trivial and can easily distort semantics, limiting the effectiveness of conventional SSL. In this work, we rethink SSL for tabular data and propose Separated-at-Birth Alignment (SeBA), a joint-embedding framework for SS-FSL that eliminates the dependence on augmentations. Our core idea is to separate the data into two independent, but complementary views and align the representations of one view to mirror the nearest-neighbor correspondence of the data in the second view. Our experimental evaluation supported by a theoretical analysis justifies that SeBA generates an output space, which improves the feature-label relationship. An experimental study conducted in various benchmark datasets demonstrates that SeBA achieves the state-of-the-art performance in the majority of cases, opening a new avenue for SS-FSL paradigm in the domain of tabular data.