Designing interpretable molecular property predictors
Name
1192539457-MIT.pdf
Size
817.75 KB
Format
Adobe PDF
Checksum (MD5)
06b2680a89d8c4e6ef8ffa8d03132003
Author(s)
Buduma, Nithin.
Advisor(s)
Tommi S. Jaakkola.
Date Issued
2020
Publisher
Massachusetts Institute of Technology
Abstract
Complex neural models often suffer from a lack of interpretability, i.e., they lack methodology for justifying their predictions. For example, while there have been many performance improvements in molecular property prediction, these advances have come in the form of black box models. As deep learning and chemistry are becoming increasingly intertwined, it is imperative that we continue to investigate interpretability of associated models. We propose a method to augment property predictors with extractive rationalization, where the model selects a subset of the input, or rationale, that it believes to be most relevant for the property of interest. These rationales serve as the model's explanations for its decisions. We show that our methodology can generate reasonable rationales while also maintaining predictive performance, and propose some future directions.
Description
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, May, 2020
Cataloged from the official PDF of thesis.
Includes bibliographical references (pages 47-48).
Subjects
Electrical Engineering and Computer Science.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided.
Persistent DSpace Link
