ICML 2022spotlight6 citations

Prototype Based Classification from Hierarchy to Fairness

Mycal Tucker, Julie A. Shah

Abstract

Artificial neural nets can represent and classify many types of high-dimensional data but are often tailored to particular applications – e.g., for “fair” or “hierarchical” classification. Once an architecture has been selected, it is often difficult for humans to adjust models for a new task; for example, a hierarchical classifier cannot be easily transformed into a fair classifier that shields a protected field. Our contribution in this work is a new neural network architecture, the concept subspace network (CSN), which generalizes existing specialized classifiers to produce a unified model capable of learning a spectrum of multi-concept relationships. We demonstrate that CSNs reproduce state-of-the-art results in fair classification when enforcing concept independence, may be transformed into hierarchical classifiers, or may even reconcile fairness and hierarchy within a single classifier. The CSN is inspired by and matches the performance of existing prototype-based classifiers that promote interpretability.

BibTeX
@InProceedings{pmlr-v162-tucker22a,
  title = 	 {Prototype Based Classification from Hierarchy to Fairness},
  author =       {Tucker, Mycal and Shah, Julie A.},
  booktitle = 	 {Proceedings of the 39th International Conference on Machine Learning},
  pages = 	 {21884--21900},
  year = 	 {2022},
  editor = 	 {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan},
  volume = 	 {162},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {17--23 Jul},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v162/tucker22a/tucker22a.pdf},
  url = 	 {https://proceedings.mlr.press/v162/tucker22a.html},
  abstract = 	 {Artificial neural nets can represent and classify many types of high-dimensional data but are often tailored to particular applications – e.g., for “fair” or “hierarchical” classification. Once an architecture has been selected, it is often difficult for humans to adjust models for a new task; for example, a hierarchical classifier cannot be easily transformed into a fair classifier that shields a protected field. Our contribution in this work is a new neural network architecture, the concept subspace network (CSN), which generalizes existing specialized classifiers to produce a unified model capable of learning a spectrum of multi-concept relationships. We demonstrate that CSNs reproduce state-of-the-art results in fair classification when enforcing concept independence, may be transformed into hierarchical classifiers, or may even reconcile fairness and hierarchy within a single classifier. The CSN is inspired by and matches the performance of existing prototype-based classifiers that promote interpretability.}
}