用神经网络表示建模人类选例策略，发现联合代表性最贴近真实教学行为。
What Makes a Good Example? Modeling Exemplar Selection with Neural Network Representations
- 用预训练视觉模型将新类别嵌入一维形态连续体，量化代表性和多样性。
- 联合代表性策略比单一原型或多样性策略更接近人类选例判断。
- 基于Transformer的表征比卷积网络更契合人类教学行为，适合教学模拟。
教学需要将丰富的类别分布浓缩为少量信息量高的范例。尽管先前研究指出人类在教学时会兼顾代表性与多样性，但其背后的计算机制仍不明确。本文通过神经网络特征表示和严谨的子集选择准则，建模人类范例选择行为。新视觉类别被嵌入一维形态连续体，由预训练视觉模型生成表征，不同选择策略侧重原型性、联合代表性或多样性。成年参与者选择1至3个范例用于教学。模型与人类行为对比显示，基于联合代表性的策略，或其与多样性的结合，最能拟合人类判断；而纯原型或纯多样性策略表现较差。此外，Transformer表征始终比卷积网络更贴近人类行为。结果表明，数据集提炼方法可作为机器学习中的教学计算模型。
原文摘要 · Abstract (English)
Teaching requires distilling a rich category distribution into a small set of informative exemplars. Although prior work shows that humans consider both representativeness and diversity when teaching, the computational principles underlying these tradeoffs remain unclear. We address this gap by modeling human exemplar selection using neural network feature representations and principled subset selection criteria. Novel visual categories were embedded along a one-dimensional morph continuum using pretrained vision models, and selection strategies varied in their emphasis on prototypicality, joint representativeness, and diversity. Adult participants selected one to three exemplars to teach a learner. Model-human comparisons revealed that strategies based on joint representativeness, or its combination with diversity, best captured human judgments, whereas purely prototypical or diversity-based strategies performed worse. Moreover, transformer-based representations consistently aligned more closely with human behavior than convolutional networks. These results highlight the potential utility of dataset distillation methods in machine learning as computational models for teaching.
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。