用概率主题模型揭示模型决策的深层语义，解释更清晰且快30倍以上。
ProToMEx: Rapid, Interpretable Explanations via Structured Representations
- 用概率主题模型挖掘分类背后的高阶语义原因，而非单一特征重要性。
- 在标准表格与合成数据上，局部解释速度比SHAP和LIME快30-40倍。
- 既能全局看模型行为，也能拆解单个预测的多重合理原因，适合实时应用。
现有机器学习分类器的后处理解释方法主要关注特征归因，为各特征分配重要性分数。尽管有价值，但此类方法难以描述驱动模型决策的复杂组合模式。为此，我们提出ProToMEx，一种基于概率主题模型（PTMs）的新解释范式。该模型无关框架可学习隐含的“主题”，代表分类的独立高层原因，超越简单特征重要性，揭示底层语义结构。ProToMEx自然提供模型整体行为的全局解释，以及可分解多个共存原因的局部解释。实验证明，ProToMEx生成的解释保真度与SHAP和LIME相当，且生成局部解释的摊销计算成本大幅降低，特别适合实时应用。具体而言，在标准化表格数据和合成数据上，其速度比SHAP和LIME快约30-40倍。
原文摘要 · Abstract (English)
Existing post-hoc explainers for machine learning classifiers primarily focus on feature attribution, assigning importance scores to individual features. While valuable, this approach struggles to articulate the complex, combinatorial patterns that often drive a model's decision-making process. To overcome this limitation, we introduce ProToMEx, a new paradigm for explainability that leverages Probabilistic Topic Models (PTMs). Our model-agnostic framework learns latent ''topics'' that represent distinct, high-level reasons for a classification, moving beyond simple feature importance to reveal underlying semantic structures. ProToMEx naturally provides both global explanations of a model's overall behaviour and local explanations that can disentangle multiple co-existing reasons for a specific prediction. We demonstrate empirically that ProToMEx not only produces explanations of comparable fidelity to popular methods like SHAP and LIME but also drastically reduces the amortised computational cost of generating local explanations, making it highly suitable for real-time applications. Specifically, we show that ProToMEx is ~30-40x faster than SHAP and LIME over standardised tabular datasets and synthetic datasets.
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。