通过最优传输实现几何数据集距离
Geometric Dataset Distances via Optimal Transport
摘要：
任务相似性的概念是各种机器学习范例的核心，例如领域自适应和元学习。目前量化它的方法通常是启发式的，对跨任务的标签集做出强有力的假设，并且许多是依赖于架构的，依赖于特定于任务的最佳参数（例如，需要在每个数据集上训练模型）。在这项工作中，我们提出了一个数据集之间距离的替代概念，（i）是模型不可知的，（ii）不涉及训练，（iii）即使它们的标签集完全不相交，也可以比较数据集，（iv）具有坚实的理论基础。这个距离依赖于最佳传输，这为它提供了丰富的几何意识，可解释的对应关系和良好理解的属性。我们的研究结果表明，这种新的距离提供了有意义的数据集比较，并与各种实验设置和数据集之间的迁移学习硬度相关。
英文摘要：
The notion of task similarity is at the core of various machine learning paradigms, such as domain adaptation and meta-learning. Current methods to quantify it are often heuristic, make strong assumptions on the label sets across the tasks, and many are architecture-dependent, relying on task-specific optimal parameters (e.g., require training a model on each dataset). In this work we propose an alternative notion of distance between datasets that (i) is model-agnostic, (ii) does not involve training, (iii) can compare datasets even if their label sets are completely disjoint and (iv) has solid theoretical footing. This distance relies on optimal transport, which provides it with rich geometry awareness, interpretable correspondences and well-understood properties. Our results show that this novel distance provides meaningful comparison of datasets, and correlates well with transfer learning hardness across various experimental settings and datasets.
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。
