Right on Time: Revising Time Series Models by Constraining their Explanations
The reliability of deep time series models is often compromised by their tendency to rely on confounding factors, which may lead to incorrect outputs. Our newly recorded, naturally confounded dataset named P2S from a real mechanical production line emphasizes this. To avoid "Clever-Hans" moments in time series, i.e., to mitigate confounders, we introduce the method Right on Time (RioT). RioT enables, for the first time, interactions with model explanations across both the time and frequency domain. Feedback on explanations in both domains is then used to constrain the model, steering it away from the annotated confounding factors. The dual-domain interaction strategy is crucial for effectively addressing confounders in time series datasets. We empirically demonstrate that RioT can effectively guide models away from the wrong reasons in P2S as well as popular time series classification and forecasting datasets.
Code (1)
Tasks
Time SeriesTime Series ClassificationSimilar Papers 제목 키워드 기반
Continuity and Ordinality Matter: Constraining Time Series Tokens for Effective Time Series Analysis with Large Language Models
Token-based time series large language models (TS-LLMs) have emerged as a promising direction for time series analysis and reasoning. However, prior studies largely overlook the inherent continuity and ordinality of time…
Time Series AnalysisEnhancing Lexicon-Based Review Classification by Merging and Revising Sentiment Dictionaries
Neural Inference of Gaussian Processes for Time Series Data of Quasars
The study of quasar light curves poses two problems: inference of the power spectrum and interpolation of an irregularly sampled time series. A baseline approach to these tasks is to interpolate a time series with a Damp…
Gaussian ProcessesTime SeriesTime Series AnalysisScalable inference of spatial regions and temporal signatures from time series
Regionalization aims to partition a spatial domain into contiguous regions that share similar characteristics, enabling more effective spatial analysis, policy making, and resource management. Existing approaches for spa…
Time Series ClusteringRestricted or Not: A General Training Framework for Neural Machine Translation
Restricted machine translation incorporates human prior knowledge into translation. It restricts the flexibility of the translation to satisfy the demands of translation in specific scenarios. Existing work typically imp…
Machine TranslationTranslation