Conference
Aug 2026
Prototype-Guided Dynamic Margin Learning for Imbalanced Time-Series Classification
Time-series classifiers trained with cross-entropy often inherit the class-frequency bias of the training set, especially when rare classes are also poorly separated in the latent feature space. This paper presents ProtoMargin, a prototype-guided dynamic margin loss for imbalanced time-series classification. The loss m...
Chang-Dong Li, Wen-Hua Ouyang, Shi-Kang Liu et al.
· 2026 12th International Conf... · 0 citations