发表机构
Radboud University Nijmegen; Delft University of Technology; University of the West of England (UWE)（拉德堡德大学奈梅亨分校; 代尔夫特理工大学; 西英格兰大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
TriProbe提出多层级探测框架，通过分解多任务为二分子任务并应用三个探针，利用最大Fisher判别比度量可分离性，诊断任务失败瓶颈，指导数据与架构设计。
AI 中文摘要
现代学习流程的评估往往简化为下游准确率，这留下了任务为何成功或失败的问题。TriProbe通过一个多层级探测框架来解决这一空白，用于任务可分离性的可解释诊断。TriProbe不将模型视为黑箱，而是追踪可分离性如何在输入、学习特征和最终分类器之间演变。它将多任务问题分解为二分子任务，并应用三个互补的探针：输入空间上的基础探针、特征表示上的潜在探针以及分类器输出上的最终探针。使用最大Fisher判别比作为原则性的可分离性度量，TriProbe识别瓶颈和受影响的任务对。在Roshambo sEMG基准上的实验展示了TriProbe如何揭示隐藏的故障，指导数据收集、验证和架构设计。
英文摘要
Modern evaluation of learning pipelines often reduces to downstream accuracy, leaving open the question of why tasks succeed or fail. TriProbe addresses this gap with a multi-level probing framework for explainable diagnosis of task separability. Rather than treating models as black boxes, TriProbe traces how separability evolves across inputs, learned features, and final classifiers. It decomposes multi-task problems into binary subtasks and applies three complementary probes: a Foundational Probe on input spaces, a Latent Probe on feature representations, and a Final Probe on classifier outputs. Using Maximum Fisher's Discriminant Ratio as a principled separability metric, TriProbe identifies bottlenecks and affected task pairs. Experiments on the Roshambo sEMG benchmark show how TriProbe reveals hidden breakdowns, guiding data collection, validation, and architecture design.
Comments5 pages, 3 figures, 16 references
