Mind the Gap: A Generative Approach to Interpretable Feature Selection and Extraction
Author(s)
Doshi-Valez, Finale; Kim, Been; Shah, Julie A
DownloadShah_MInd the gap.pdf (881.2Kb)
PUBLISHER_POLICY
Publisher Policy
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Terms of use
Metadata
Show full item recordAbstract
We 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
Date issued
2015Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence LaboratoryJournal
Advances in Neural Information Processing Systems 28 (NIPS 2015)
Publisher
Neural Information Processing Systems Foundation Inc.
Citation
Kim, Been, Julie A Shah, and Finale Doshi-Velez. “Mind the Gap: A Generative Approach to Interpretable Feature Selection and Extraction.” Advances in Neural Information Processing Systems 28. Ed. C Cortes et al. Curran Associates, Inc., 2015. 2260–2268.
Version: Final published version