算法推荐改进建议可能因大家集体行动而失效，需只基于因果变量建议。
Performative Validity of Recourse Explanations
- 基于因果变量推荐改变，避免非因果变量干扰导致建议失效。
- 若多人按建议改变输入，数据分布变化会使原模型决策边界失效。
- 警告使用标准反事实解释和因果推理方法，易产生无效建议。
当申请人被算法系统拒绝时，可操作的解释会提供修改输入特征以获得正面评估的具体建议。一个关键却被忽视的现象是：这些解释具有表演性（performative）——当大量申请人采纳建议并改变自身行为时，整体数据的统计规律会发生变化；一旦模型重新训练，决策边界也随之变动，导致原先的建议变得无效。这意味着，即便申请人付出努力实施建议，再次申请时仍可能被拒绝。本文形式化地刻画了在何种条件下，可操作解释能保持有效性。核心发现表明，若建议涉及或干预非因果变量，其有效性将丧失。据此，我们警示不应使用标准反事实解释和因果性可操作方法，而应优先采用仅基于因果变量提出建议的方法。
原文摘要 · Abstract (English)
When applicants get rejected by an algorithmic decision system, recourse explanations provide actionable suggestions for how to change their input features to get a positive evaluation. A crucial yet overlooked phenomenon is that recourse explanations are performative: When many applicants act according to their recommendations, their collective behavior may change statistical regularities in the data and, once the model is refitted, also the decision boundary. Consequently, the recourse algorithm may render its own recommendations invalid, such that applicants who make the effort of implementing their recommendations may be rejected again when they reapply. In this work, we formally characterize the conditions under which recourse explanations remain valid under performativity. A key finding is that recourse actions may become invalid if they are influenced by or if they intervene on non-causal variables. Based on our analysis, we caution against the use of standard counterfactual explanations and causal recourse methods, and instead advocate for recourse methods that recommend actions exclusively on causal variables.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。