LGCVMLApr 20, 2020

Local Clustering with Mean Teacher for Semi-supervised Learning

arXiv:2004.09665v27 citations
Originality Incremental advance
AI Analysis

This addresses a specific problem of confirmation bias in semi-supervised learning for researchers and practitioners, offering an incremental enhancement to an existing method.

The paper tackled confirmation bias in the Mean Teacher model for semi-supervised learning by introducing a Local Clustering method that clusters data points in feature space to pull misclassified unlabeled points towards correct class regions, resulting in significant improvements over MT and performance comparable to state-of-the-art on SVHN and CIFAR-10 datasets.

The Mean Teacher (MT) model of Tarvainen and Valpola has shown favorable performance on several semi-supervised benchmark datasets. MT maintains a teacher model's weights as the exponential moving average of a student model's weights and minimizes the divergence between their probability predictions under diverse perturbations of the inputs. However, MT is known to suffer from confirmation bias, that is, reinforcing incorrect teacher model predictions. In this work, we propose a simple yet effective method called Local Clustering (LC) to mitigate the effect of confirmation bias. In MT, each data point is considered independent of other points during training; however, data points are likely to be close to each other in feature space if they share similar features. Motivated by this, we cluster data points locally by minimizing the pairwise distance between neighboring data points in feature space. Combined with a standard classification cross-entropy objective on labeled data points, the misclassified unlabeled data points are pulled towards high-density regions of their correct class with the help of their neighbors, thus improving model performance. We demonstrate on semi-supervised benchmark datasets SVHN and CIFAR-10 that adding our LC loss to MT yields significant improvements compared to MT and performance comparable to the state of the art in semi-supervised learning.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes