Multi-group Learning for Hierarchical Groups
This work addresses generalization challenges for overlapping subgroups in hierarchical settings, representing an incremental advancement in multi-group learning.
The paper tackles the problem of multi-group learning with hierarchical group structures by designing an algorithm that outputs an interpretable decision tree predictor with near-optimal sample complexity, achieving attractive generalization properties on real datasets.
The multi-group learning model formalizes the learning scenario in which a single predictor must generalize well on multiple, possibly overlapping subgroups of interest. We extend the study of multi-group learning to the natural case where the groups are hierarchically structured. We design an algorithm for this setting that outputs an interpretable and deterministic decision tree predictor with near-optimal sample complexity. We then conduct an empirical evaluation of our algorithm and find that it achieves attractive generalization properties on real datasets with hierarchical group structure.