Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.02239 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911740494610432 |
|---|---|
| author | De Felice, Giovanni D'Elia, Riccardo Termine, Alberto Barbiero, Pietro Marra, Giuseppe Santini, Silvia |
| author_facet | De Felice, Giovanni D'Elia, Riccardo Termine, Alberto Barbiero, Pietro Marra, Giuseppe Santini, Silvia |
| contents | Deep time series models continue to improve predictive performance, yet their deployment remains limited by their black-box nature. In response, existing interpretability approaches in the field keep focusing on explaining the internal model computations, without addressing whether they align or not with how a human would reason about the studied phenomenon. Instead, we state interpretability in deep time series models should pursue semantic alignment: predictions should be expressed in terms of variables that are meaningful to the end user, mediated by spatial and temporal mechanisms that admit user-dependent constraints. In this paper, we formalize this requirement and state that, once established, semantic alignment must be preserved under temporal evolution: a constraint with no analog in static settings. Provided with this definition, we outline a blueprint for semantically aligned deep time series models, identify properties that support trust, and discuss implications for model design. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_02239 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Interpretability in Deep Time Series Models Demands Semantic Alignment De Felice, Giovanni D'Elia, Riccardo Termine, Alberto Barbiero, Pietro Marra, Giuseppe Santini, Silvia Machine Learning Deep time series models continue to improve predictive performance, yet their deployment remains limited by their black-box nature. In response, existing interpretability approaches in the field keep focusing on explaining the internal model computations, without addressing whether they align or not with how a human would reason about the studied phenomenon. Instead, we state interpretability in deep time series models should pursue semantic alignment: predictions should be expressed in terms of variables that are meaningful to the end user, mediated by spatial and temporal mechanisms that admit user-dependent constraints. In this paper, we formalize this requirement and state that, once established, semantic alignment must be preserved under temporal evolution: a constraint with no analog in static settings. Provided with this definition, we outline a blueprint for semantically aligned deep time series models, identify properties that support trust, and discuss implications for model design. |
| title | Interpretability in Deep Time Series Models Demands Semantic Alignment |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2602.02239 |