研究人员开发了一个新框架，以应对为机器学习模型基准测试选择代表性数据集的挑战。该框架旨在通过识别更小、更有效的数据子集来降低评估成本，这些子集能够保持大型基准测试中发现的全局模型排名。该研究介绍了各种选择策略，包括引导聚合和贪婪最远优先方法，并评估了它们在时间序列分类和自然语言处理等不同领域的有效性。 AI
影响 这项研究通过减少对广泛数据集的需求，可能带来更高效、更具成本效益的机器学习模型评估。
排序理由 该集群包含一篇研究论文，详细介绍了用于机器学习基准测试的数据集选择新框架。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.27997v1 Announce Type: cross Abstract: Benchmarks of machine learning models often include many datasets, making evaluation expensive. For efficiency, it is preferable to perform evaluations on small, representative datasets instead. The selection of such subsets typic…
Benchmarks of machine learning models often include many datasets, making evaluation expensive. For efficiency, it is preferable to perform evaluations on small, representative datasets instead. The selection of such subsets typically relies on heuristics and is rarely analyzed f…