Consistent algorithms for multi-label classification with macro-at-$k$ metrics. (arXiv:2401.16594v1 [cs.LG])

We consider the optimization of complex performance metrics in multi-label
classification under the population utility framework. We mainly focus on
metrics linearly decomposable into a sum of binary classification utilities
applied separately to each label with an additional requirement of exactly $k$
labels predicted for each instance. These "macro-at-$k$" metrics possess
desired properties for extreme classification problems with long tail labels.
Unfortunately, the at-$k$ constraint couples the otherwise independent binary
classification tasks, leading to a much more challenging optimization problem …

algorithms arxiv binary classification consistent cs.lg focus framework instance labels macro metrics optimization performance population utilities utility