Paper Detail
Hongnan Ma, Yiwei Shi, Mengyue Yang, Weiru Liu
Faithful explanations of time-series classifiers should identify subsequences that are not only sufficient to preserve a black-box model's prediction, but also necessary for maintaining it. However, existing sufficiency-oriented methods can assign high importance to spurious subsequences that support the prediction without being essential to the model's decision. We introduce \textbf{TimePNS}, a necessity-aware framework for time-series explanation. Inspired by Pearl's counterfactual notion of necessity, TimePNS assesses whether a temporal factor is necessary by intervening on it and measuring whether the original prediction is disrupted. The framework adopts a two-stage design. Stage I learns an identifiable causal generative process together with a sufficiency-oriented explanation mask. Stage II performs counterfactual interventions on temporal factors to derive necessity signals, which supervise a temporal gate that refines the initial explanation by suppressing non-essential components and emphasizing counterfactually necessary ones. Experiments on synthetic and real-world time-series benchmarks show that TimePNS more accurately identifies decision-critical subsequences and consistently improves sufficiency-necessity trade-offs over strong baselines.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@article{ma2026beyond,
title = {Beyond Sufficiency: Time Series Explanation with Counterfactual Necessity},
author = {Hongnan Ma and Yiwei Shi and Mengyue Yang and Weiru Liu},
year = {2026},
abstract = {Faithful explanations of time-series classifiers should identify subsequences that are not only sufficient to preserve a black-box model's prediction, but also necessary for maintaining it. However, existing sufficiency-oriented methods can assign high importance to spurious subsequences that support the prediction without being essential to the model's decision. We introduce \textbackslash{}textbf\{TimePNS\}, a necessity-aware framework for time-series explanation. Inspired by Pearl's counterfactual notion of n},
url = {https://arxiv.org/abs/2607.21573},
keywords = {cs.LG, cs.AI},
eprint = {2607.21573},
archiveprefix = {arXiv},
}
{}