Asymmetric Polynomial Loss For Multi-Label Classification
This work addresses performance issues in multi-label classification for researchers and practitioners, though it is incremental as it builds on existing loss functions.
The paper tackles the suboptimal performance of binary cross-entropy loss in multi-label classification due to its inability to adapt to diverse tasks and sample imbalance, proposing an Asymmetric Polynomial Loss that improves performance across relation extraction, text classification, and image classification tasks without extra training burden.
Various tasks are reformulated as multi-label classification problems, in which the binary cross-entropy (BCE) loss is frequently utilized for optimizing well-designed models. However, the vanilla BCE loss cannot be tailored for diverse tasks, resulting in a suboptimal performance for different models. Besides, the imbalance between redundant negative samples and rare positive samples could degrade the model performance. In this paper, we propose an effective Asymmetric Polynomial Loss (APL) to mitigate the above issues. Specifically, we first perform Taylor expansion on BCE loss. Then we ameliorate the coefficients of polynomial functions. We further employ the asymmetric focusing mechanism to decouple the gradient contribution from the negative and positive samples. Moreover, we validate that the polynomial coefficients can recalibrate the asymmetric focusing hyperparameters. Experiments on relation extraction, text classification, and image classification show that our APL loss can consistently improve performance without extra training burden.