Multilabel ranking is a central task in machine learning with widespread applications to web search, news stories, recommender systems, etc. However, the most fundamental question of learnability in a multilabel ranking setting remains unanswered. In this paper, we characterize the learnability of multilabel ranking problems in both the batch and online settings for a large family of ranking losses. Along the way, we also give the first equivalence class of ranking losses based on learnability.

翻译：多标签排序是机器学习中的核心任务，广泛应用于网页搜索、新闻推荐、推荐系统等领域。然而，在多标签排序场景下，最根本的可学习性问题仍未得到解答。本文针对大规模排序损失函数族，系统刻画了批处理与在线设置中多标签排序问题的可学习性。在此过程中，我们首次基于可学习性构建了排序损失函数的等价类。