# Integrating Distribution Matching into Semi-Supervised Contrastive Learning for Labeled and Unlabeled Data

Source: [Integrating Distribution Matching into Semi-Supervised Contrastive Learning for Labeled and Unlabeled Data](<https://www.sota2.com/research/paper/69608b6353fdd5c3617440e0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-10T05:00:05.200Z

Authors: Shogo Nakayama, Masahiro Okuda

Published: 2026-01-08T02:32:12.000Z

## Abstract

The advancement of deep learning has greatly improved supervised image classification. However, labeling data is costly, prompting research into unsupervised learning methods such as contrastive learning. In real-world scenarios, fully unlabeled datasets are rare, making semi-supervised learning (SSL) highly relevant in scenarios where a small amount of labeled data coexists with a large volume of unlabeled data. A well-known semi-supervised contrastive learning approach involves assigning pseudo-labels to unlabeled data. This study aims to enhance pseudo-label-based SSL by incorporating distribution matching between labeled and unlabeled feature embeddings to improve image classification accuracy across multiple datasets.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2601.04518>)

[PDF](<https://arxiv.org/pdf/2601.04518.pdf>)