Leveraging Sparse Linear Layers for Debuggable Deep Networks

11 May 2021  ·  Eric Wong, Shibani Santurkar, Aleksander Mądry ·

We show how fitting sparse linear models over learned deep feature representations can lead to more debuggable neural networks. These networks remain highly accurate while also being more amenable to human interpretation, as we demonstrate quantiatively via numerical and human experiments. We further illustrate how the resulting sparse explanations can help to identify spurious correlations, explain misclassifications, and diagnose model biases in vision and language tasks. The code for our toolkit can be found at https://github.com/madrylab/debuggabledeepnetworks.

PDF Abstract

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.


No methods listed for this paper. Add relevant methods here