Top-rank learning identifies a real-valued ranking function that will provide more absolute top samples. These are highly reliable positive samples that are ranked higher than the highest-ranked negative samples. Therefore, top-rank learning is useful for tasks that require reliable decisions. Additionally, it inherits the merits of the ranking functions, such as robustness to the unbalanced condition. However, conventional top-rank learning tasks are formulated as linear or kernel-based problems and are thus limited in coping with complicated tasks. In this study, we propose a Top-rank convolutional neural network (TopRank CNN) to realize top-rank learning with representation learning for complicated tasks. Given that the original objective function of top-rank learning suffers from overfitting, we employ the $p$-norm relaxation of the original loss function in the proposed method. We prove the usefulness of TopRank CNN experimentally with medical diagnosis tasks that require reliable decisions and robustness to the unbalanced condition.

排名靠前的学习确定了一个实值排名函数，它将提供更多的绝对排名样品。这些是高度可靠的正样本，其排名高于排名最高的负样本。因此，顶级学习对于需要可靠决策的任务很有用。此外，它继承了排序函数的优点，例如对不平衡条件的鲁棒性。然而，传统的顶级学习任务被表述为线性或基于核的问题，因此在处理复杂任务方面受到限制。在这项研究中，我们提出了一个顶级卷积神经网络（TopRank CNN）来实现顶级学习和复杂任务的表征学习。鉴于顶级学习的原始目标函数存在过拟合问题，我们采用$磷$- 所提出方法中原始损失函数的范数松弛。我们通过实验证明了 TopRank CNN 对医学诊断任务的有用性，这些任务需要可靠的决策和对不平衡条件的鲁棒性。