Improving Detection of Rare Nodes in Hierarchical Multi-Label Learning
This work addresses the problem of fine-grained classification in hierarchical structures for machine learning practitioners, offering an incremental improvement over existing methods.
The paper tackled the challenge of detecting rare nodes in hierarchical multi-label classification by proposing a weighted loss objective that combines node-wise imbalance and focal weighting, resulting in up to a fivefold improvement in recall and significant gains in F1 score on benchmark datasets.
In hierarchical multi-label classification, a persistent challenge is enabling model predictions to reach deeper levels of the hierarchy for more detailed or fine-grained classifications. This difficulty partly arises from the natural rarity of certain classes (or hierarchical nodes) and the hierarchical constraint that ensures child nodes are almost always less frequent than their parents. To address this, we propose a weighted loss objective for neural networks that combines node-wise imbalance weighting with focal weighting components, the latter leveraging modern quantification of ensemble uncertainties. By emphasizing rare nodes rather than rare observations (data points), and focusing on uncertain nodes for each model output distribution during training, we observe improvements in recall by up to a factor of five on benchmark datasets, along with statistically significant gains in $F_{1}$ score. We also show our approach aids convolutional networks on challenging tasks, as in situations with suboptimal encoders or limited data.