Neighborhood-Regularized Self-Training for Learning with Few Labels

TL;DR

This paper introduces a neighborhood-regularized self-training method that improves learning with few labels by reducing pseudo label noise and stabilizing training, leading to better performance across multiple tasks.

Contribution

The authors propose a neighborhood-based sample selection and prediction aggregation approach to enhance self-training for semi-supervised learning with limited labels.

Findings

Outperforms strong self-training baselines with 1.83% and 2.51% gains.

Reduces pseudo label noise by 36.8%.

Saves 57.3% of training time.

Abstract

Training deep neural networks (DNNs) with limited supervision has been a popular research topic as it can significantly alleviate the annotation burden. Self-training has been successfully applied in semi-supervised learning tasks, but one drawback of self-training is that it is vulnerable to the label noise from incorrect pseudo labels. Inspired by the fact that samples with similar labels tend to share similar representations, we develop a neighborhood-based sample selection approach to tackle the issue of noisy pseudo labels. We further stabilize self-training via aggregating the predictions from different rounds during sample selection. Experiments on eight tasks show that our proposed method outperforms the strongest self-training baseline with 1.83% and 2.51% performance gain for text and graph datasets on average. Our further analysis demonstrates that our proposed data selection strategy reduces the noise of pseudo labels by 36.8% and saves 57.3% of the time when compared with the best baseline. Our code and appendices will be uploaded to https://github.com/ritaranx/NeST.