DP-SSL: Towards Robust Semi-supervised Learning with A Few Labeled Samples

TL;DR

DP-SSL introduces an innovative data programming approach with automatic label functions and a label model to improve semi-supervised learning performance when labeled data is scarce, outperforming existing methods on standard benchmarks.

Contribution

The paper proposes a novel DP-SSL method that automatically generates labeling functions and infers probabilistic labels, enhancing SSL stability and accuracy with minimal labeled data.

Findings

DP-SSL achieves higher accuracy than state-of-the-art SSL methods on CIFAR-10 with only 40 labeled samples.

DP-SSL provides reliable labels for unlabeled data, improving classification performance.

Experimental results demonstrate DP-SSL's effectiveness across four SSL benchmarks.

Abstract

The scarcity of labeled data is a critical obstacle to deep learning. Semi-supervised learning (SSL) provides a promising way to leverage unlabeled data by pseudo labels. However, when the size of labeled data is very small (say a few labeled samples per class), SSL performs poorly and unstably, possibly due to the low quality of learned pseudo labels. In this paper, we propose a new SSL method called DP-SSL that adopts an innovative data programming (DP) scheme to generate probabilistic labels for unlabeled data. Different from existing DP methods that rely on human experts to provide initial labeling functions (LFs), we develop a multiple-choice learning~(MCL) based approach to automatically generate LFs from scratch in SSL style. With the noisy labels produced by the LFs, we design a label model to resolve the conflict and overlap among the noisy labels, and finally infer probabilistic labels for unlabeled samples. Extensive experiments on four standard SSL benchmarks show that DP-SSL can provide reliable labels for unlabeled data and achieve better classification performance on test sets than existing SSL methods, especially when only a small number of labeled samples are available. Concretely, for CIFAR-10 with only 40 labeled samples, DP-SSL achieves 93.82% annotation accuracy on unlabeled data and 93.46% classification accuracy on test data, which are higher than the SOTA results.