Multi-Label Learning from Single Positive Labels - CVPR 2021

noisy labels; missing labels; semi-supervised learning; entropy; uncertainty; robustness and generalisation.

SMiLE algorithm for multilabel classification for missing labels

[2024 ACM MM] Official PyTorch implementation of the paper "Text-Region Matching for Multi-Label Image Recognition with Missing Labels"

The proposed method captures local and global correlations using Low Rank label subspace transformation for Multi-label learning with Missing Labels (LRMML). The model considers an auxiliary label matrix which facilitates the missing label information recovery.

To deal with the issues emerging from incomplete labels and high-dimensional input space, we propose a multi-label learning approach based on identifying the label-specific features and constraining them with a sparse global structure. The sparse structural constraint helps maintain the typical characteristics of the multi-label learning data.

[KDD 2025] Code for the paper "On the Necessity of World Knowledge for Mitigating Missing Labels in Extreme Classification"

To deal with the class imbalance problem in multi-label learning with missing labels, we propose Class Imbalance aware Missing labels Multi-label Learning, CIMML. Our proposed method handles class imbalance issue by constructing a label weight matrix with weight estimation guided by how frequently a label is present, absent, and unobserved.

In this paper, we propose an approach for multi-label classification when label details are incomplete by learning auxiliary label matrix from the observed labels, and generating an embedding from learnt label correlations preserving the correlation structure in model coefficients.