检验已有反事实解释方法在数据缺失时的表现，发现均难生成有效解释。
Evaluating Counterfactual Explanation Methods on Incomplete Inputs
- 在输入不完整时评估多种反事实解释生成方法的性能。
- 所有方法在缺失数据下生成有效反事实的能力都很弱。
- 研究结果呼吁开发能处理不完整输入的新解释方法。
现有的机器学习反事实解释（CX）生成算法通常假设输入数据是完整的。然而，现实世界数据常包含缺失值，而现有CX方法在不完整输入下的表现尚未被系统研究。为填补这一空白，我们系统评估了近期的CX生成方法在输入缺失时生成有效且合理反事实的能力。基于假设：鲁棒的CX生成方法应更适应不完整输入的挑战，我们的研究发现，尽管鲁棒方法在有效性上优于非鲁棒方法，但所有方法在输入缺失时仍难以找到有效的反事实。这一结果凸显了开发能够处理不完整输入的新一代反事实解释方法的迫切需求。
原文摘要 · Abstract (English)
Existing algorithms for generating Counterfactual Explanations (CXs) for Machine Learning (ML) typically assume fully specified inputs. However, real-world data often contains missing values, and the impact of these incomplete inputs on the performance of existing CX methods remains unexplored. To address this gap, we systematically evaluate recent CX generation methods on their ability to provide valid and plausible counterfactuals when inputs are incomplete. As part of this investigation, we hypothesize that robust CX generation methods will be better suited to address the challenge of providing valid and plausible counterfactuals when inputs are incomplete. Our findings reveal that while robust CX methods achieve higher validity than non-robust ones, all methods struggle to find valid counterfactuals. These results motivate the need for new CX methods capable of handling incomplete inputs.
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。