iCubed (Institute, Industry, Innovation) seminars invite DSI Industry Affiliates to give technical talks on work going on in their domain. Join to learn about real-world uses of data science and opportunities with Industry Affiliates.


Guest Speakers

Brian Barr, Machine Learning Researcher, Capital One

Matthew Harrington, PhD Student, School of International and Public Affairs (SIPA), Columbia University

Moderated By: John Hyde, DSI Assistant Director of Career Development and Alumni Services


Details

Thursday, December 2 (3:00 PM – 4:00 PM ET) – Virtual


Talk Details

Counterfactual Explanations via Latent Space Projection and Interpolation

Counterfactual explanations represent the minimal change to a data sample that alters its predicted classification, typically from an unfavorable initial class to a desired target class. Counterfactuals can help answer questions like “what needs to change for this loan application to get accepted?”.  A number of recently proposed approaches to counterfactual generation are computationally intensive and provide unconvincing explanations.  

We will discuss a new method dubbed SharpShooter, that starts by creating a projection of the input that classifies as the target class. Counterfactual candidates are then generated in latent space on the interpolation line between the input and its projection. We demonstrate that our framework translates core characteristics of a sample to its counterfactual through the use of learned representations. In addition, we show that SharpShooter is competitive across common quality metrics, excels at measures of realism,  while being three orders of magnitude faster than comparable methods – making it well-suited for high velocity machine learning applications which require timely explanations.