Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning
This addresses a critical limitation in SSL for applications with imbalanced data, though it is an incremental improvement over existing SSL methods.
The paper tackles the problem of semi-supervised learning (SSL) algorithms performing poorly under imbalanced class distributions by proposing DARP, a method to refine biased pseudo-labels, which improves compatibility with state-of-the-art SSL schemes in various imbalanced scenarios.
While semi-supervised learning (SSL) has proven to be a promising way for leveraging unlabeled data when labeled data is scarce, the existing SSL algorithms typically assume that training class distributions are balanced. However, these SSL algorithms trained under imbalanced class distributions can severely suffer when generalizing to a balanced testing criterion, since they utilize biased pseudo-labels of unlabeled data toward majority classes. To alleviate this issue, we formulate a convex optimization problem to softly refine the pseudo-labels generated from the biased model, and develop a simple algorithm, named Distribution Aligning Refinery of Pseudo-label (DARP) that solves it provably and efficiently. Under various class-imbalanced semi-supervised scenarios, we demonstrate the effectiveness of DARP and its compatibility with state-of-the-art SSL schemes.