Mind the Gap: A Generative Approach to Interpretable Feature Selection and Extraction

TitleMind the Gap: A Generative Approach to Interpretable Feature Selection and Extraction
Publication TypeConference Proceedings
Year of Conference2015
AuthorsKim, B., J. Shah, and F. Doshi-Velez
Conference NameAdvances in Neural Information Processing Systems (NIPS)
Date Published12/2015
AbstractWe present the Mind the Gap Model (MGM), an approach for interpretable feature extraction and selection. By placing interpretability criteria directly into the model, we allow for the model to both optimize parameters related to interpretability and to directly report a global set of distinguishable dimensions to assist with further data exploration and hypothesis generation. MGM extracts distinguishing features on real-world datasets of animal features, recipes ingredients, and disease co-occurrence. It also maintains or improves performance when compared to related approaches. We perform a user study with domain experts to show the MGM’s ability to help with dataset exploration.
URLhttp://interactive.mit.edu/sites/default/files/documents/BKim2015NIPS.pdf
Refereed DesignationRefereed