OWAdapt: An adaptive loss function for deep learning using OWA operators
This addresses class imbalance and noise in classification for deep learning practitioners, but it is incremental as it builds on existing loss functions with fuzzy logic enhancements.
The paper tackles the problem of class-level noise and imbalance in deep learning classification by proposing a fuzzy adaptive loss function based on OWA operators, which outperforms standard cross-entropy and focal loss across various tasks.
In this paper, we propose a fuzzy adaptive loss function for enhancing deep learning performance in classification tasks. Specifically, we redefine the cross-entropy loss to effectively address class-level noise conditions, including the challenging problem of class imbalance. Our approach introduces aggregation operators, leveraging the power of fuzzy logic to improve classification accuracy. The rationale behind our proposed method lies in the iterative up-weighting of class-level components within the loss function, focusing on those with larger errors. To achieve this, we employ the ordered weighted average (OWA) operator and combine it with an adaptive scheme for gradient-based learning. Through extensive experimentation, our method outperforms other commonly used loss functions, such as the standard cross-entropy or focal loss, across various binary and multiclass classification tasks. Furthermore, we explore the influence of hyperparameters associated with the OWA operators and present a default configuration that performs well across different experimental settings.