A JEPA-based model with domain-informed multi-view self-distillation learns light-curve representations that outperform hand-crafted features on 15 of 16 StarEmbed metrics and adapts competitively to other irregular time-series datasets.
Data Mining and Knowl- edge Discovery 38, 1958–2031 (2024)
5 Pith papers cite this work, alongside 154 external citations. Polarity classification is still indexing.
5
Pith papers citing it
154
external citations · OpenAlex
citation-role summary
method 1
citation-polarity summary
verdicts
UNVERDICTED 5roles
method 1polarities
use method 1representative citing papers
DiffTW derives a diffeomorphic dissimilarity from transport equation characteristics using ODEs and RKHS optimal control, outperforming DTW on 60 of 86 datasets with 1-NN.
RocketPFN matches the accuracy of the strongest time series classifier HC2 on 92 UCR datasets using a training-free pipeline of Rocket features and TabPFN.
Fusing chart visualizations with raw time series improves or maintains classification accuracy on UCR datasets when the visuals add non-redundant information.
Synthetic experiments reveal that class-dependent effects appear in both perturbation-based and ground-truth evaluations of time series feature attributions, often producing contradictory rankings of attribution quality due to differences in feature amplitude or temporal extent between classes.
citing papers explorer
-
Domain-Informed Multi-View Self-Distillation for Astronomical Light-Curve Representation Learning with JEPA
A JEPA-based model with domain-informed multi-view self-distillation learns light-curve representations that outperform hand-crafted features on 15 of 16 StarEmbed metrics and adapts competitively to other irregular time-series datasets.
-
Time Series Classification through Diffeomorphic Time Warping (DiffTW)
DiffTW derives a diffeomorphic dissimilarity from transport equation characteristics using ODEs and RKHS optimal control, outperforming DTW on 60 of 86 datasets with 1-NN.
-
RocketPFN: Accurate Time Series Classification via In-Context Learning
RocketPFN matches the accuracy of the strongest time series classifier HC2 on 92 UCR datasets using a training-free pipeline of Rocket features and TabPFN.
-
VTBench: A Multimodal Framework for Time-Series Classification with Chart-Based Representations
Fusing chart visualizations with raw time series improves or maintains classification accuracy on UCR datasets when the visuals add non-redundant information.
-
Why Do Class-Dependent Evaluation Effects Occur with Time Series Feature Attributions? A Synthetic Data Investigation
Synthetic experiments reveal that class-dependent effects appear in both perturbation-based and ground-truth evaluations of time series feature attributions, often producing contradictory rankings of attribution quality due to differences in feature amplitude or temporal extent between classes.