Timezone: »

What went wrong and when? Instance-wise feature importance for time-series black-box models
Sana Tonekaboni · Shalmali Joshi · Kieran Campbell · David Duvenaud · Anna Goldenberg

Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ Poster Session 3 #1069

Explanations of time series models are useful for high stakes applications like healthcare but have received little attention in machine learning literature. We propose FIT, a framework that evaluates the importance of observations for a multivariate time-series black-box model by quantifying the shift in the predictive distribution over time. FIT defines the importance of an observation based on its contribution to the distributional shift under a KL-divergence that contrasts the predictive distribution against a counterfactual where the rest of the features are unobserved. We also demonstrate the need to control for time-dependent distribution shifts. We compare with state-of-the-art baselines on simulated and real-world clinical data and demonstrate that our approach is superior in identifying important time points and observations throughout the time series.

Author Information

Sana Tonekaboni (University of Toronto / Vector Institute)
Shalmali Joshi (Harvard University (SEAS))
Kieran Campbell (University of British Columbia)
David Duvenaud (University of Toronto)

David Duvenaud is an assistant professor in computer science at the University of Toronto. His research focuses on continuous-time models, latent-variable models, and deep learning. His postdoc was done at Harvard University, and his Ph.D. at the University of Cambridge. David also co-founded Invenia, an energy forecasting and trading company.

Anna Goldenberg

More from the Same Authors