Learning Generalized Label Distributions

Haitao Wu, Weiwei Li, Kun Yue, Xiuyi Jia

Keywords: generalized label distribution, label distribution learning, multi-label learning

Abstract: Label ambiguity is pervasive in supervised learning, motivating a variety of representations beyond the traditional single-label setting. While label distribution (LD) provides a probabilistic description and has attracted increasing attention, we reveal its inherent limitations, including inconsistency with raw data, distortion of inter-sample order, and limited applicability. To address these issues, we introduce generalized label distribution (GLD), a unified representation that can perfectly recover raw data while preserving inter-sample order consistency, transform into existing forms of label representations without information loss, and capture out-of-distribution samples as well as negative label correlations. We further develop GLD learning algorithms and demonstrate their effectiveness through both theoretical analysis and extensive experiments.

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

Submission Number: 10853