Emblaze：通过嵌入空间的交互式比较阐明机器学习表示
Emblaze: Illuminating Machine Learning Representations through Interactive Comparison of Embedding Spaces
摘要：
现代机器学习技术通常依赖于复杂的高维嵌入表示来捕获数据中的底层结构并提高性能。为了表征模型缺陷并选择理想的表示，模型构建者通常需要在多个嵌入空间中进行比较，这是一项具有挑战性的分析任务，现有工具很少支持。我们首先采访了不同领域的九位嵌入专家，以描述他们在分析嵌入空间时面临的各种挑战和使用的技术。根据这些观点，我们开发了一种名为Emblaze的新系统，该系统将嵌入空间比较集成在计算笔记本环境中。Emblaze使用动画，交互式散点图与新颖的星迹增强，使视觉比较。它还采用了新的邻域分析和聚类程序，以动态地建议空间之间有有趣变化的点组。通过与ML专家的一系列案例研究，我们展示了如何与Emblaze进行交互式比较，以帮助获得对嵌入空间结构的新见解。
英文摘要：
Modern machine learning techniques commonly rely on complex, high-dimensional embedding representations to capture underlying structure in the data and improve performance. In order to characterize model flaws and choose a desirable representation, model builders often need to compare across multiple embedding spaces, a challenging analytical task supported by few existing tools. We first interviewed nine embedding experts in a variety of fields to characterize the diverse challenges they face and techniques they use when analyzing embedding spaces. Informed by these perspectives, we developed a novel system called Emblaze that integrates embedding space comparison within a computational notebook environment. Emblaze uses an animated, interactive scatter plot with a novel Star Trail augmentation to enable visual comparison. It also employs novel neighborhood analysis and clustering procedures to dynamically suggest groups of points with interesting changes between spaces. Through a series of case studies with ML experts, we demonstrate how interactive comparison with Emblaze can help gain new insights into embedding space structure.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
