GenFacts-Generative Counterfactual Explanations for Multi-Variate Time Series
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910024246231040 |
|---|---|
| author | Seifi, Sarah Ibrahimi, Anass Sukianto, Tobias Carbonelli, Cecilia Servadei, Lorenzo Wille, Robert |
| author_facet | Seifi, Sarah Ibrahimi, Anass Sukianto, Tobias Carbonelli, Cecilia Servadei, Lorenzo Wille, Robert |
| contents | Counterfactual explanations aim to enhance model transparency by showing how inputs can be minimally altered to change predictions. For multivariate time series, existing methods often generate counterfactuals that are invalid, implausible, or unintuitive. We introduce GenFacts, a generative framework based on a class-discriminative variational autoencoder. It integrates contrastive and classification-consistency objectives, prototype-based initialization, and realism-constrained optimization. We evaluate GenFacts on radar gesture data as an industrial use case and handwritten letter trajectories as an intuitive benchmark. Across both datasets, GenFacts outperforms state-of-the-art baselines in plausibility (+18.7%) and achieves the highest interpretability scores in a human study. These results highlight that plausibility and user-centered interpretability, rather than sparsity alone, are key to actionable counterfactuals in time series data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_20936 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GenFacts-Generative Counterfactual Explanations for Multi-Variate Time Series Seifi, Sarah Ibrahimi, Anass Sukianto, Tobias Carbonelli, Cecilia Servadei, Lorenzo Wille, Robert Machine Learning Counterfactual explanations aim to enhance model transparency by showing how inputs can be minimally altered to change predictions. For multivariate time series, existing methods often generate counterfactuals that are invalid, implausible, or unintuitive. We introduce GenFacts, a generative framework based on a class-discriminative variational autoencoder. It integrates contrastive and classification-consistency objectives, prototype-based initialization, and realism-constrained optimization. We evaluate GenFacts on radar gesture data as an industrial use case and handwritten letter trajectories as an intuitive benchmark. Across both datasets, GenFacts outperforms state-of-the-art baselines in plausibility (+18.7%) and achieves the highest interpretability scores in a human study. These results highlight that plausibility and user-centered interpretability, rather than sparsity alone, are key to actionable counterfactuals in time series data. |
| title | GenFacts-Generative Counterfactual Explanations for Multi-Variate Time Series |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.20936 |