用线性变换融合全局与局部解释，提升表格数据模型可解释性。
Explanations Go Linear: Post-hoc Explainability for Tabular Data with Interpretable Meta-Encoding
- 用元编码学习实例特异性线性变换，结合全局代理模型。
- 在多个数据集上实现高精度且稳定的特征归因与决策规则。
- 适合需要高效、鲁棒解释的工业级表格数据应用。
后处理可解释性对理解黑箱机器学习模型至关重要。基于代理的方法广泛用于局部和全局模型无关解释，但存在明显局限：局部代理能捕捉非线性关系，但计算开销大且对参数敏感；全局代理更高效，却难以刻画复杂局部行为。本文提出ILLUME框架，基于表示学习，可与多种代理模型集成，为任意黑箱分类器提供解释。其核心思想是将全局训练的代理模型与通过元编码学习的实例特异性线性变换相结合，生成兼具局部与全局解释能力的结果。大量实证评估表明，ILLUME能生成准确、稳健且计算高效的特征归因与决策规则，有效克服传统代理方法的不足，构建统一的解释范式。
原文摘要 · Abstract (English)
Post-hoc explainability is essential for understanding black-box machine learning models. Surrogate-based techniques are widely used for local and global model-agnostic explanations but have significant limitations. Local surrogates capture non-linearities but are computationally expensive and sensitive to parameters, while global surrogates are more efficient but struggle with complex local behaviors. In this paper, we present ILLUME, a flexible and interpretable framework grounded in representation learning, that can be integrated with various surrogate models to provide explanations for any black-box classifier. Specifically, our approach combines a globally trained surrogate with instance-specific linear transformations learned with a meta-encoder to generate both local and global explanations. Through extensive empirical evaluations, we demonstrate the effectiveness of ILLUME in producing feature attributions and decision rules that are not only accurate but also robust and computationally efficient, thus providing a unified explanation framework that effectively addresses the limitations of traditional surrogate methods.
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。