Multi-group Learning for Hierarchical Groups

Samuel Deng, Daniel Hsu
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10440-10487, 2024.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-deng24a, title = {Multi-group Learning for Hierarchical Groups}, author = {Deng, Samuel and Hsu, Daniel}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {10440--10487}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/deng24a/deng24a.pdf}, url = {https://proceedings.mlr.press/v235/deng24a.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Multi-group Learning for Hierarchical Groups %A Samuel Deng %A Daniel Hsu %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-deng24a %I PMLR %P 10440--10487 %U https://proceedings.mlr.press/v235/deng24a.html %V 235 %X 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.
APA
Deng, S. & Hsu, D.. (2024). Multi-group Learning for Hierarchical Groups. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:10440-10487 Available from https://proceedings.mlr.press/v235/deng24a.html.

Related Material