实时生成多样且准确的可解释模型，让非专家也能快速修正机器学习缺陷。
Rashomon Sets for Prototypical-Part Networks: Editing Interpretable Models in Real-Time
- 通过构建瑞雪曼集，一次性生成多个性能相当的可解释模型。
- 在鸟类识别和皮肤癌检测中成功消除人为偏见并修复模型错误。
- 无需重训，让临床等非专业人士即时调试模型，提升可解释性与实用性。
可解释性对高风险场景下的机器学习模型至关重要，它使用户能够验证模型推理过程。在计算机视觉领域，原型部件网络（ProtoPNets）已成为满足这一需求的主流模型类型。用户虽能轻松发现ProtoPNet中的问题，但修复却需耗时且困难的重新训练，且无法保证问题解决。该问题被称为“交互瓶颈”。本文提出一种新框架——Proto-RSet，通过同时寻找多个性能相当的ProtoPNets（即“瑞雪曼集”抽样），解决此瓶颈。实验表明，该方法能快速生成多个准确且多样化的ProtoPNets，使用户在保持训练集性能保障的前提下，实时纠正模型缺陷。我们在两个场景中验证了其有效性：1）移除鸟类识别模型中的人工引入偏见；2）调试皮肤癌识别模型。该工具赋能非机器学习专家（如临床医生或领域专家）无需反复依赖专家重训，即可快速优化和修正模型。
原文摘要 · Abstract (English)
Interpretability is critical for machine learning models in high-stakes settings because it allows users to verify the model's reasoning. In computer vision, prototypical part models (ProtoPNets) have become the dominant model type to meet this need. Users can easily identify flaws in ProtoPNets, but fixing problems in a ProtoPNet requires slow, difficult retraining that is not guaranteed to resolve the issue. This problem is called the "interaction bottleneck." We solve the interaction bottleneck for ProtoPNets by simultaneously finding many equally good ProtoPNets (i.e., a draw from a "Rashomon set"). We show that our framework - called Proto-RSet - quickly produces many accurate, diverse ProtoPNets, allowing users to correct problems in real time while maintaining performance guarantees with respect to the training set. We demonstrate the utility of this method in two settings: 1) removing synthetic bias introduced to a bird identification model and 2) debugging a skin cancer identification model. This tool empowers non-machine-learning experts, such as clinicians or domain experts, to quickly refine and correct machine learning models without repeated retraining by machine learning experts.
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。