AI Paper Atlas

Research map / Time series / Foundation models for time series

Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency

Owen Queen, Thomas Hartvigsen, Teddy Koker, Huan He, Theodoros Tsiligkaridis, Marinka Zitnik

NeurIPS 2023 · Time series › Foundation models for time series · approach: Time series representation learning

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
use discrete straight-through estimator masks instead of soft attention masking (ablation)TimeX · ECGexplanation AUPRC: 0.4014 -> 0.4721Improved
use discrete STE masks instead of soft masks (ablation)TimeX · ECGexplanation AUR: 0.1564 -> 0.4457Improved
align explanation latent space with SimCLR loss instead of MBC (ablation)TimeX · ECGexplanation AUP: 0.5663 -> 0.4895Hurt
align explanation latent space with SimCLR loss instead of MBC (ablation)TimeX · ECGexplanation AUPRC: 0.4721 -> 0.4767No clear effect
use only the model behavior consistency (MBC) objective (ablation)TimeX · ECGexplanation AUPRC: 0.4721 -> 0.1615Hurt
use only the label consistency (LC) objective (ablation)TimeX · ECGexplanation AUPRC: 0.4721 -> 0.3704Hurt
combine MBC and LC objectives (ablation)TimeX · ECGexplanation AUPRC: 0.1615 -> 0.4721Improved
TimeX instead of strongest baselineTimeX · synthetic datasetsexplanation AUP: 3.07% on FreqShapes, 6.3% on SeqComb-UV, 8.43% on SeqComb-MV, 6.24% on LowVarImproved
TimeX instead of strongest baselineTimeX · ECGexplanation AUPRC: 0.4182 -> 0.4721Improved
TimeX instead of Integrated GradientsTimeX · ECGexplanation AUP: 0.5949 -> 0.5663Hurt
TimeX instead of IGTimeX · LowVarexplanation AUPRC: 0.8691 -> 0.8673No clear effect
TimeX instead of Dynamask under occlusionTimeX · Boilerclassification AUROC under occlusion: 27.8% average, up to 37.4% at the 0.75 thresholdImproved

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