[论文解读] One Explanation Does Not Fit All: The Promise of Interactive Explanations for Machine Learning Transparency

Kacper Sokol, Peter Flach|Explore Bristol Research|Jan 27, 2020

Explainable Artificial Intelligence (XAI)参考文献 38被引用 33

一句话总结

论文主张在机器学习中提供真正的交互式、个性化解释，提出 Glass-Box 作为用于贷款模型的类别对比反事实解释器，并讨论交互式 XAI 系统的愿望清单、风险与评估方法。

ABSTRACT

The need for transparency of predictive systems based on Machine Learning algorithms arises as a consequence of their ever-increasing proliferation in the industry. Whenever black-box algorithmic predictions influence human affairs, the inner workings of these algorithms should be scrutinised and their decisions explained to the relevant stakeholders, including the system engineers, the system's operators and the individuals whose case is being decided. While a variety of interpretability and explainability methods is available, none of them is a panacea that can satisfy all diverse expectations and competing objectives that might be required by the parties involved. We address this challenge in this paper by discussing the promises of Interactive Machine Learning for improved transparency of black-box systems using the example of contrastive explanations -- a state-of-the-art approach to Interpretable Machine Learning. Specifically, we show how to personalise counterfactual explanations by interactively adjusting their conditional statements and extract additional explanations by asking follow-up "What if?" questions. Our experience in building, deploying and presenting this type of system allowed us to list desired properties as well as potential limitations, which can be used to guide the development of interactive explainers. While customising the medium of interaction, i.e., the user interface comprising of various communication channels, may give an impression of personalisation, we argue that adjusting the explanation itself and its content is more important. To this end, properties such as breadth, scope, context, purpose and target of the explanation have to be considered, in addition to explicitly informing the explainee about its limitations and caveats...

研究动机与目标

• 激发在工业界对透明 ML 系统的需求，以及一刀切解释的局限性。
• 提出一个利用反事实的交互式个性化解释架构。
• 使用贷款批准模型演示并评估一个交互式解释器（Glass-Box）。
• 确定交互式解释器的愿望清单、挑战与安全考虑。
• 提供开发交互式 XAI 工具的指南与未来研究方向。

提出的方法

• 将交互式解释及对比性反事实作为核心机制进行呈现。
• 开发 Glass-Box，一种基于决策树分类器、支持语音和文本输入的交互式对比性反事实解释器。
• 在二元元特征空间中使用叶到叶距离度量来生成最小化的反事实解释。
• 通过自然语言对话支持互动查询（Why?, Why given?, Why despite?, What if?）。
• 标注数据集以实现对公平性及其他属性的解释，并使用 Google AIY Voice Kit 部署。

(a) Default segmentation.

实验结果

研究问题

• RQ1 如何使解释个性化并可交互地操作，以更好地满足解释对象的需求？
• RQ2 哪些属性和愿望清单应指导真正的交互式 XAI 系统的设计？
• RQ3 在现实世界部署交互式解释器时，实际挑战和安全关切是什么？
• RQ4 如何在交互式对话中生成并导航反事实解释？
• RQ5 在部署和评估端到端的交互式解释器时，涌现出哪些指南？

主要发现

• 交互式解释可以通过内容、范围和呈现方式来个性化，而不仅仅是媒介。
• 通过自然语言对话交付的类别对比反事实解释是一种自然直观的解释形式。
• 端到端的交互式解释器需要整合 UI、NLP、NLG、对话管理和 XAI 算法。
• 允许自由操作解释时存在重要的安全与隐私风险，例如训练数据或模型信息的潜在泄露。
• 建议在全面部署前进行 Wizard-of-Oz 研究，作为测试交互式可解释性算法的代理。
• 使用 Glass-Box 的经验为构建交互式、个性化解释提供了具体的愿望清单和经验教训。

(b) User-merged segmentation.