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

TL;DR

SeBA introduces a novel semi-supervised few-shot learning framework for tabular data that aligns independent data views without relying on data augmentations, achieving state-of-the-art results.

Contribution

SeBA presents a new joint-embedding approach for SS-FSL on tabular data that eliminates the need for data augmentations and improves feature-label relationships.

Findings

SeBA outperforms existing methods on multiple benchmark datasets.

Theoretical analysis supports improved feature-label relationships.

Achieves state-of-the-art performance in semi-supervised few-shot learning for tabular data.

Abstract

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.