AI Paper Atlas

Research map / Time series / Causal and generative time series

Learning Perturbations to Explain Time Series Predictions

Joseph Enguehard

ICML 2023 · Time series › Causal and generative time series · approach: Robust forecasting and evaluation · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Learn a perturbation generator jointly with the mask instead of using a fixed perturbationTime-series saliency explanations · HMMAUR: DynaMask 0.763 (0.026) -> Ours 0.781 (0.013)Improved
Learn a perturbation generator jointly with the mask instead of using fixed perturbationsTime-series saliency explanations · MIMIC-III, 20% masked, average replacementCross-Entropy: IG 0.098 (0.006) -> Ours 0.118 (0.008)Improved
Use deletion game instead of preservation game (ablation)Learned perturbation method · HMMAUP: 0.885 (0.030) -> 0.346 (0.0034)Hurt
Use deletion game instead of preservation game (ablation)Learned perturbation method · HMMAUR: 0.781 (0.013) -> 0.863 (0.012)Improved
Use deletion game instead of preservation game (ablation)Learned perturbation method · MIMIC-III, zero replacement, 20% maskedCross-Entropy: 0.318 (0.057) -> 0.079 (0.012)Hurt
Use a unidirectional GRU rather than a Bi-GRU perturbation generator (ablation)Learned perturbation method · MIMIC-III, 20% masked, average replacementCross-Entropy: 0.118 (0.008) -> 0.122 (0.004)Improved
Use a unidirectional GRU rather than a Bi-GRU perturbation generator (ablation)Learned perturbation method · MIMIC-III, 20% masked, zero replacementCross-Entropy: 1.09E-1 (0.023) -> 1.22E-1 (0.008)Improved
Replace the learned perturbation generator with fixed zeros (ablation)Learned perturbation method · MIMIC-III, 20% masked, zero replacementCross-Entropy: 1.22E-1 (0.008) -> 9.64E-2 (0.013)Hurt
Set lambda_1 close to 1 rather than very low or very high (ablation)Learned perturbation method · HMMAUP: 0.51 - 0.81; 0.89 - 0.75; 0.99 - 0.26Mixed
Increase lambda_2 to at least 1 to regularize the perturbation generator (ablation)Learned perturbation method · HMMAUP: 0.51 - 0.81 -> 0.89 - 0.75Improved
Use low lambda_1 values rather than constraining the mask strongly (ablation)Learned perturbation method · MIMIC-IIIAccuracy: 0.926 - 0.348 -> 0.881- 0.534Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy