English

Interpretable Set Functions

Machine Learning 2018-06-04 v1 Artificial Intelligence Machine Learning

Abstract

We propose learning flexible but interpretable functions that aggregate a variable-length set of permutation-invariant feature vectors to predict a label. We use a deep lattice network model so we can architect the model structure to enhance interpretability, and add monotonicity constraints between inputs-and-outputs. We then use the proposed set function to automate the engineering of dense, interpretable features from sparse categorical features, which we call semantic feature engine. Experiments on real-world data show the achieved accuracy is similar to deep sets or deep neural networks, and is easier to debug and understand.

Keywords

Cite

@article{arxiv.1806.00050,
  title  = {Interpretable Set Functions},
  author = {Andrew Cotter and Maya Gupta and Heinrich Jiang and James Muller and Taman Narayan and Serena Wang and Tao Zhu},
  journal= {arXiv preprint arXiv:1806.00050},
  year   = {2018}
}