[论文解读] Hybrid Decision Making: When Interpretable Models Collaborate With Black-Box Models.

Tong Wang|arXiv (Cornell University)|Feb 12, 2018

Explainable Artificial Intelligence (XAI)参考文献 32被引用 6

一句话总结

本文提出 CoBRUSH，一种混合决策模型，通过将可解释的规则集与黑箱模型相结合，实现准确且可解释的预测。该模型首先将实例路由至规则；若无规则适用，则由黑箱模型介入，其准确率与仅使用黑箱模型相当或更优，同时提升了可解释性并降低了模型复杂度。

ABSTRACT

Interpretable machine learning models have received increasing interest in recent years, especially in domains where humans are involved in the decision-making process. However, the possible loss of the task performance for gaining interpretability is often inevitable. This performance downgrade puts practitioners in a dilemma of choosing between a top-performing black-box model with no explanations and an interpretable model with unsatisfying task performance. In this work, we propose a novel framework for building a Hybrid Decision Model that integrates an interpretable model with any black-box model to introduce explanations in the decision making process while preserving or possibly improving the predictive accuracy. We propose a novel metric, explainability, to measure the percentage of data that are sent to the interpretable model for decision. We also design a principled objective function that considers predictive accuracy, model interpretability, and data explainability. Under this framework, we develop Collaborative Black-box and RUle Set Hybrid (CoBRUSH) model that combines logic rules and any black-box model into a joint decision model. An input instance is first sent to the rules for decision. If a rule is satisfied, a decision will be directly generated. Otherwise, the black-box model is activated to decide on the instance. To train a hybrid model, we design an efficient search algorithm that exploits theoretically grounded strategies to reduce computation. Experiments show that CoBRUSH models are able to achieve same or better accuracy than their black-box collaborator working alone while gaining explainability. They also have smaller model complexity than interpretable baselines.

研究动机与目标

• 解决决策系统中模型可解释性与预测性能之间的权衡问题。
• 克服可解释模型通常在性能上逊于黑箱模型的局限性。
• 构建一个框架，在保持高预测准确率的同时引入人类可理解的解释。
• 提出一个系统性的目标函数，以平衡准确率、可解释性与数据可解释性。
• 设计一种高效的训练算法，使混合模型在不产生过高计算成本的前提下可扩展。

提出的方法

• 提出一种混合决策框架，其中输入实例首先在一组逻辑规则上进行评估。
• 若某条规则被满足，则模型直接从规则集中输出决策；否则调用黑箱模型。
• 引入一种新指标“可解释性”，用于衡量被路由至可解释模型的数据实例比例。
• 设计一个联合目标函数，同时优化预测准确率、模型可解释性与数据可解释性。
• 开发一种基于理论支撑策略的高效搜索算法，以降低训练复杂度。
• 通过联合优化规则生成与黑箱模型集成，端到端训练 CoBRUSH 模型。

实验结果

研究问题

• RQ1 混合模型是否能在保持或提升预测准确率的同时，提供人类可理解的决策？
• RQ2 被路由至可解释规则的比例（即可解释性）如何影响整体模型性能？
• RQ3 与纯可解释基线相比，该混合模型在多大程度上降低了模型复杂度？
• RQ4 对准确率、可解释性与可解释性的联合优化，在实际部署中产生何种影响？
• RQ5 所提出的训练算法是否能高效扩展至大规模数据集，同时不损害模型质量？

主要发现

• CoBRUSH 模型在预测准确率上与单独训练的黑箱模型相当或更优。
• 与纯可解释基线相比，该混合模型在模型复杂度方面表现更优。
• 大量实例被路由至可解释规则组件，显著提升了可解释性，且未牺牲性能。
• 所提出的训练算法通过理论支撑的搜索策略，有效降低了计算成本。
• 联合优化框架在实践中成功平衡了预测准确率、可解释性与数据可解释性。
• 实证结果证实，与独立的可解释模型相比，该混合方法在准确率与复杂度指标上均表现更优。