Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.12921 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912427579277312 |
|---|---|
| author | Kraus, Maurice Steinmann, David Wüst, Antonia Kokozinski, Andre Kersting, Kristian |
| author_facet | Kraus, Maurice Steinmann, David Wüst, Antonia Kokozinski, Andre Kersting, Kristian |
| contents | Deep time series models often suffer from reliability issues due to their tendency to rely on spurious correlations, leading to incorrect predictions. To mitigate such shortcuts and prevent "Clever-Hans" moments in time series models, we introduce Right on Time (RioT), a novel method that enables interacting with model explanations across both the time and frequency domains. By incorporating feedback on explanations in both domains, RioT constrains the model, steering it away from annotated spurious correlations. This dual-domain interaction strategy is crucial for effectively addressing shortcuts in time series datasets. We empirically demonstrate the effectiveness of RioT in guiding models toward more reliable decision-making across popular time series classification and forecasting datasets, as well as our newly recorded dataset with naturally occuring shortcuts, P2S, collected from a real mechanical production line. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_12921 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Right on Time: Revising Time Series Models by Constraining their Explanations Kraus, Maurice Steinmann, David Wüst, Antonia Kokozinski, Andre Kersting, Kristian Machine Learning Deep time series models often suffer from reliability issues due to their tendency to rely on spurious correlations, leading to incorrect predictions. To mitigate such shortcuts and prevent "Clever-Hans" moments in time series models, we introduce Right on Time (RioT), a novel method that enables interacting with model explanations across both the time and frequency domains. By incorporating feedback on explanations in both domains, RioT constrains the model, steering it away from annotated spurious correlations. This dual-domain interaction strategy is crucial for effectively addressing shortcuts in time series datasets. We empirically demonstrate the effectiveness of RioT in guiding models toward more reliable decision-making across popular time series classification and forecasting datasets, as well as our newly recorded dataset with naturally occuring shortcuts, P2S, collected from a real mechanical production line. |
| title | Right on Time: Revising Time Series Models by Constraining their Explanations |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2402.12921 |