Self-PU: Self Boosted and Calibrated Positive-Unlabeled Training

TL;DR

Self-PU introduces a novel self-training framework for positive-unlabeled learning that adaptively discovers confident examples, calibrates losses, and employs teacher-student distillation, achieving state-of-the-art results on benchmarks and real-world data.

Contribution

It proposes a self-boosted, self-calibrated PU learning framework integrating self-paced training, instance-aware loss, and distillation, advancing the effectiveness of PU classifiers.

Findings

Self-PU outperforms existing methods on MNIST and CIFAR-10 benchmarks.

Self-PU achieves significant improvements on Alzheimer's Disease brain image classification.

The framework demonstrates robustness and adaptability in real-world PU learning scenarios.

Abstract

Many real-world applications have to tackle the Positive-Unlabeled (PU) learning problem, i.e., learning binary classifiers from a large amount of unlabeled data and a few labeled positive examples. While current state-of-the-art methods employ importance reweighting to design various risk estimators, they ignored the learning capability of the model itself, which could have provided reliable supervision. This motivates us to propose a novel Self-PU learning framework, which seamlessly integrates PU learning and self-training. Self-PU highlights three "self"-oriented building blocks: a self-paced training algorithm that adaptively discovers and augments confident positive/negative examples as the training proceeds; a self-calibrated instance-aware loss; and a self-distillation scheme that introduces teacher-students learning as an effective regularization for PU learning. We demonstrate the state-of-the-art performance of Self-PU on common PU learning benchmarks (MNIST and CIFAR-10), which compare favorably against the latest competitors. Moreover, we study a real-world application of PU learning, i.e., classifying brain images of Alzheimer's Disease. Self-PU obtains significantly improved results on the renowned Alzheimer's Disease Neuroimaging Initiative (ADNI) database over existing methods. The code is publicly available at: https://github.com/TAMU-VITA/Self-PU.