首页 > AI前沿 > When the tail is earned by its companions: measuring label dependence in long-tailed multi-label classification

When the tail is earned by its companions: measuring label dependence in long-tailed multi-label classification

arXiv自然语言 2026-11-17 22:38 14 阅读 查看原文

A rare label seldom occurs alone, and a classifier can recover it from the frequent labels it co-occurs with, its companions, without having learned the label itself.

Existing diagnostics of this need a trained model: none says before training whether a corpus admits the failure, or what the standard aggregate hides.

Macro-F1, like any measure built from per-label confusion counts, is unchanged by how a label's recall divides between occurrences with and without a companion.

We introduce a within-label estimand of that division, a reading rule under which a fall in dependence counts only if companion-free recall rises, and a statistic of training labels that bounds, before training, how far reported recall can exceed companion-free recall.

Across 23 corpora, 7 training objectives and five families of label-correlation mechanisms, companion-free recall falls short on all six corpora where the estimand is defined. Up to 18.4% of the tail true positives macro-F1 credits would vanish at the companion-free rate, within the training-label bound on every corpus.

No long-tail objective reduces the dependence, but architecture moves it. Models whose tail score is computed from other labels' predictions are strongly dependent.