Neighborhood-Regularized Self-Training for Learning with Few Labels

by   Ran Xu, et al.
Emory University
Georgia Institute of Technology

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 2.51 analysis demonstrates that our proposed data selection strategy reduces the noise of pseudo labels by 36.8 the best baseline. Our code and appendices will be uploaded to


page 1

page 2

page 3

page 4


Doubly Robust Self-Training

Self-training is an important technique for solving semi-supervised lear...

Meta Self-Refinement for Robust Learning with Weak Supervision

Training deep neural networks (DNNs) with weak supervision has been a ho...

Webly Supervised Image Classification with Self-Contained Confidence

This paper focuses on webly supervised learning (WSL), where datasets ar...

Iterative Pseudo-Labeling with Deep Feature Annotation and Confidence-Based Sampling

Training deep neural networks is challenging when large and annotated da...

Statistical and Algorithmic Insights for Semi-supervised Learning with Self-training

Self-training is a classical approach in semi-supervised learning which ...

URL: Combating Label Noise for Lung Nodule Malignancy Grading

Due to the complexity of annotation and inter-annotator variability, mos...

Backdoor Defense via Decoupling the Training Process

Recent studies have revealed that deep neural networks (DNNs) are vulner...

Please sign up or login with your details

Forgot password? Click here to reset