Extreme multi-label (XML) classification refers to the task of supervised multi-label learning that involves a large number of labels. Hence, scalability of the classifier with increasing label dimension is an important consideration. In this paper, we develop a method called LightDXML which modifies the recently developed deep learning based XML framework by using label embeddings instead of feature embedding for negative sampling and iterating cyclically through three major phases: (1) proxy training of label embeddings (2) shortlisting of labels for negative sampling and (3) final classifier training using the negative samples. Consequently, LightDXML also removes the requirement of a re-ranker module, thereby, leading to further savings on time and memory requirements. The proposed method achieves the best of both worlds: while the training time, model size and prediction times are on par or better compared to the tree-based methods, it attains much better prediction accuracy that is on par with the deep learning based methods. Moreover, the proposed approach achieves the best tail-label prediction accuracy over most state-of-the-art XML methods on some of the large datasets\footnote{accepted in IJCNN 2023, partial funding from MAPG grant and IIIT Seed grant at IIIT, Hyderabad, India. Code: \url{https://github.com/misterpawan/LightDXML}

翻译：极限多标签分类是指涉及大量标签的监督多标签学习任务。因此，分类器随标签维度增长的扩展性是一个重要考量。本文提出一种称为LightDXML的方法，它改进了近期基于深度学习的XML框架，通过使用标签嵌入而非特征嵌入进行负采样，并以循环方式迭代执行三个主要阶段：（1）标签嵌入的代理训练；（2）用于负采样的标签候选列表生成；（3）利用负样本进行最终分类器训练。因此，LightDXML还移除了重排序模块的需求，从而进一步节省时间和内存需求。所提出的方法实现了两全其美：训练时间、模型大小和预测时间与基于树的方法相当或更优，同时获得了与深度学习方法相媲美的更好预测精度。此外，所提方法在一些大型数据集上，在大多数最先进的XML方法中实现了最佳尾部标签预测精度\footnote{已被IJCNN 2023录用，部分资助来自MAPG基金和印度海得拉巴IIIT的IIIT种子基金。代码：\url{https://github.com/misterpawan/LightDXML}}。