Towards Macro-AUC oriented Imbalanced Multi-Label Continual Learning

TL;DR

This paper introduces a novel method for optimizing Macro-AUC in imbalanced multi-label continual learning, combining a reweighted loss and memory strategy, with theoretical analysis and experimental validation.

Contribution

It proposes a new RLDAM loss and WRU memory strategy tailored for Macro-AUC optimization in imbalanced MLCL, with the first theoretical generalization analysis in this setting.

Findings

The proposed method outperforms several baselines.

Theoretical analysis confirms superior generalization in MLCL.

Experimental results validate effectiveness across datasets.

Abstract

In Continual Learning (CL), while existing work primarily focuses on the multi-class classification task, there has been limited research on Multi-Label Learning (MLL). In practice, MLL datasets are often class-imbalanced, making it inherently challenging, a problem that is even more acute in CL. Due to its sensitivity to imbalance, Macro-AUC is an appropriate and widely used measure in MLL. However, there is no research to optimize Macro-AUC in MLCL specifically. To fill this gap, in this paper, we propose a new memory replay-based method to tackle the imbalance issue for Macro-AUC-oriented MLCL. Specifically, inspired by recent theory work, we propose a new Reweighted Label-Distribution-Aware Margin (RLDAM) loss. Furthermore, to be compatible with the RLDAM loss, a new memory-updating strategy named Weight Retain Updating (WRU) is proposed to maintain the numbers of positive and negative instances of the original dataset in memory. Theoretically, we provide superior generalization analyses of the RLDAM-based algorithm in terms of Macro-AUC, separately in batch MLL and MLCL settings. This is the first work to offer theoretical generalization analyses in MLCL to our knowledge. Finally, a series of experimental results illustrate the effectiveness of our method over several baselines. Our codes are available at https://github.com/ML-Group-SDU/Macro-AUC-CL.