One Positive Label is Sufficient: Single-Positive Multi-Label Learning with Label Enhancement
This work addresses the problem of reducing annotation effort for multi-label classification tasks, making it more practical for real-world applications, though it is an incremental improvement over existing methods.
The paper tackles the challenge of high annotation costs in multi-label learning by proposing a method that requires only one positive label per training example, showing that this is sufficient to train a predictive model with theoretical guarantees and competitive performance on benchmark datasets.
Multi-label learning (MLL) learns from the examples each associated with multiple labels simultaneously, where the high cost of annotating all relevant labels for each training example is challenging for real-world applications. To cope with the challenge, we investigate single-positive multi-label learning (SPMLL) where each example is annotated with only one relevant label, and show that one can successfully learn a theoretically grounded multi-label classifier for the problem. In this paper, a novel SPMLL method named SMILE, i.e., Single-positive MultI-label learning with Label Enhancement, is proposed. Specifically, an unbiased risk estimator is derived, which could be guaranteed to approximately converge to the optimal risk minimizer of fully supervised learning and shows that one positive label of each instance is sufficient to train the predictive model. Then, the corresponding empirical risk estimator is established via recovering the latent soft label as a label enhancement process, where the posterior density of the latent soft labels is approximate to the variational Beta density parameterized by an inference model. Experiments on benchmark datasets validate the effectiveness of the proposed method.