---
title: "超越充分性：基于反事实必要性的时间序列解释"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.21573v1"
permalink: "https://feed.astralor.com/items/itm_b9c3cfef30d504c04a0f1f98"
published: "2026-07-23T17:52:01.000Z"
score: 79
channel: "ai"
tags: ["TimePNS","反事实必要性","可解释AI","因果推断","时间序列解释"]
---

# 超越充分性：基于反事实必要性的时间序列解释

## AI 点评

> 在可解释AI热潮中，多数方法默认寻找“足够”的理由，却忽略了“必要”的边界。TimePNS通过因果干预精准定位模型真正依赖的时间片段，这对风险敏感场景的模型审计价值极高。推荐给从事时间序列建模、可解释性研究以及监管合规方向的研究者和工程师。

## 速览

现有时间序列分类器解释方法通常只关注子序列是否足以维持预测（充分性），却可能将非必要的虚假特征赋予高重要性。本文提出TimePNS框架，借鉴Pearl的反事实必要性思想，通过主动干预时间因子并观察预测是否被破坏来评估其必要性。框架分为两阶段：阶段I学习可识别的因果生成过程与充分性掩码；阶段II对时间因子进行反事实干预，产生必要性信号来指导一个时间门控，从而细化解释——抑制非必要成分、强调反事实必要的部分。在合成和真实时间序列基准上的实验表明，TimePNS能更准确地识别决策关键子序列，并在充分性-必要性权衡上持续优于强基线。

## 关键点

- 现有充分性导向方法易受虚假特征干扰，必要性被忽视。
- TimePNS引入反事实必要性评估，通过干预时间因子区分真正关键的子序列。
- 两阶段框架：因果生成+充分掩码（阶段I）与反事实干预+门控细化（阶段II）。
- 在多个基准上显著提升解释准确性与充分性-必要性平衡。

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_b9c3cfef30d504c04a0f1f98