EXPLOR: Extrapolatory Pseudo-Label Matching for OOD Uncertainty Based Rejection

ICLR 2026 Conference Submission10082 Authors

Keywords: OOD Generalization, Pseudo-labeling, reject option

Abstract: EXPLOR is a novel framework that utilizes support-expanding, extrapolatory pseudo-labeling to improve prediction and uncertainty-based rejection on out-of-distribution (OOD) points. EXPLOR utilizes a diverse set of pseudo-labelers on an expansive augmented dataset to improve OOD performance through multiple MLP heads (one per pseudo-labeler) with shared embedding trained with a novel per-head matching loss. Unlike prior methods that rely on modality-specific augmentations or assume access to OOD data, EXPLOR introduces extrapolatory pseudo-labeling on latent-space augmentations, enabling robust OOD generalization with any real-valued vector data. In contrast to prior modality-agnostic methods with neural backbones, EXPLOR is model-agnostic, working effectively with methods from simple tree-based models to complex OOD generalization models. We demonstrate that EXPLOR achieves superior performance compared to state-of-the-art methods on diverse datasets in single-source domain generalization settings.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Submission Number: 10082