Noisy-Pair Robust Representation Alignment for Positive-Unlabeled Learning
It addresses the bottleneck of learning discriminative representations in PU learning for applications like post-disaster damage mapping, offering a novel method without auxiliary information, though it appears incremental as it builds on existing PU frameworks.
The paper tackles the problem of Positive-Unlabeled (PU) learning, where classifiers underperform due to unreliable supervision, and proposes NcPU, a non-contrastive framework that improves performance, achieving substantial gains over state-of-the-art methods on diverse datasets like CIFAR-100 with a 14.26% gap reduction.
Positive-Unlabeled (PU) learning aims to train a binary classifier (positive vs. negative) where only limited positive data and abundant unlabeled data are available. While widely applicable, state-of-the-art PU learning methods substantially underperform their supervised counterparts on complex datasets, especially without auxiliary negatives or pre-estimated parameters (e.g., a 14.26% gap on CIFAR-100 dataset). We identify the primary bottleneck as the challenge of learning discriminative representations under unreliable supervision. To tackle this challenge, we propose NcPU, a non-contrastive PU learning framework that requires no auxiliary information. NcPU combines a noisy-pair robust supervised non-contrastive loss (NoiSNCL), which aligns intra-class representations despite unreliable supervision, with a phantom label disambiguation (PLD) scheme that supplies conservative negative supervision via regret-based label updates. Theoretically, NoiSNCL and PLD can iteratively benefit each other from the perspective of the Expectation-Maximization framework. Empirically, extensive experiments demonstrate that: (1) NoiSNCL enables simple PU methods to achieve competitive performance; and (2) NcPU achieves substantial improvements over state-of-the-art PU methods across diverse datasets, including challenging datasets on post-disaster building damage mapping, highlighting its promise for real-world applications. Code: Code will be open-sourced after review.