Algorithms designed for addressing typical supervised classification problems can only learn from a fixed set of samples and labels, making them unsuitable for the real world, where data arrives as a stream of samples often associated with multiple labels over time. This motivates the study of task-agnostic continual multi-label learning problems. While algorithms using deep learning approaches for continual multi-label learning have been proposed in the recent literature, they tend to be computationally heavy. Although spiking neural networks (SNNs) offer a computationally efficient alternative to artificial neural networks, existing literature has not used SNNs for continual multi-label learning. Also, accurately determining multiple labels with SNNs is still an open research problem. This work proposes a dual output spiking architecture (DOSA) to bridge these research gaps. A novel imbalance-aware loss function is also proposed, improving the multi-label classification performance of the model by making it more robust to data imbalance. A modified F1 score is presented to evaluate the effectiveness of the proposed loss function in handling imbalance. Experiments on several benchmark multi-label datasets show that DOSA trained with the proposed loss function shows improved robustness to data imbalance and obtains better continual multi-label learning performance than CIFDM, a previous state-of-the-art algorithm.

翻译：针对典型监督分类问题设计的算法只能从固定样本和标签集中学习，难以适应真实世界中数据以流形式到达且常伴随多标签关联的场景，由此推动了任务无关持续多标签学习问题的研究。尽管近年文献中已提出基于深度学习的持续多标签学习算法，但其普遍存在计算开销大的缺陷。虽然脉冲神经网络（SNNs）提供了比人工神经网络更高效的计算替代方案，但现有文献尚未将SNNs应用于持续多标签学习；同时，如何利用SNNs准确确定多标签仍是一个开放研究问题。本研究提出一种双输出脉冲架构（DOSA）来填补这些研究空白。我们同时设计了一种新颖的不平衡感知损失函数，通过增强模型对数据不平衡的鲁棒性来提升多标签分类性能。为评估所提出损失函数处理不平衡问题的有效性，我们引入修正后的F1分数。在多个基准多标签数据集上的实验表明，基于所提出损失函数训练的DOSA模型对数据不平衡展现出更强的鲁棒性，并在持续多标签学习性能上优于现有最先进算法CIFDM。