让模型训练过程中的公平性问题显形，支持多指标联动分析
InsightBoard: An Interactive Multi-Metric Visualization and Fairness Analysis Plugin for TensorBoard
- 通过联动图表与切片分析，实时追踪多指标变化
- 在BDD100k数据集上发现强整体性能模型仍存在显著群体差异
- 无需改动训练流程，即可在训练中诊断公平性问题
在安全关键领域部署的现代机器学习系统不仅需要关注整体性能，还需洞察训练动态对子群体公平性的影响。现有训练仪表板主要支持单一指标监控，难以分析异构指标间关系或诊断训练过程中的子群体差异。我们提出 InsightBoard，一个集成多指标同步可视化与基于切片的公平性诊断的 TensorBoard 插件。该插件通过联动多视图图表、相关性分析及用户自定义切片下的标准公平性指标，实现对训练动态、性能指标与子群体差异的联合检视。在 YOLOX 与 BDD100k 数据集的案例研究中，我们发现：即便模型具备优异的整体性能，其在人口统计学和环境条件上的差异仍可能被传统监控手段掩盖。通过在训练过程中提供公平性诊断能力，InsightBoard 支持更早、更明智的模型评估，且无需修改现有训练流程或引入额外数据存储。
原文摘要 · Abstract (English)
Modern machine learning systems deployed in safety-critical domains require visibility not only into aggregate performance but also into how training dynamics affect subgroup fairness over time. Existing training dashboards primarily support single-metric monitoring and offer limited support for examining relationships between heterogeneous metrics or diagnosing subgroup disparities during training. We present InsightBoard, an interactive TensorBoard plugin that integrates synchronized multi-metric visualization with slice-based fairness diagnostics in a unified interface. InsightBoard enables practitioners to jointly inspect training dynamics, performance metrics, and subgroup disparities through linked multi-view plots, correlation analysis, and standard group fairness indicators computed over user-defined slices. Through case studies with YOLOX on the BDD100k dataset, we demonstrate that models achieving strong aggregate performance can still exhibit substantial demographic and environmental disparities that remain hidden under conventional monitoring. By making fairness diagnostics available during training, InsightBoard supports earlier, more informed model inspection without modifying existing training pipelines or introducing additional data stores.
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。