Multi-Label Adaptive Batch Selection by Highlighting Hard and Imbalanced Samples

arXiv:2403.18192v1 Announce Type: new
Abstract: Deep neural network models have demonstrated their effectiveness in classifying multi-label data from various domains. Typically, they employ a training mode that combines mini-batches with optimizers, where each sample is randomly selected with equal probability when constructing mini-batches. However, the intrinsic class imbalance in multi-label data may bias the model towards majority labels, since samples relevant to minority labels may be underrepresented in each mini-batch. Meanwhile, during the training process, we observe that instances associated …

abstract arxiv class cs.lg data deep neural network domains highlighting however intrinsic network neural network probability sample samples training type