arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.03144cs.LG
收藏

什么使一个好的例子?用神经网络表示进行实例选择建模

What Makes a Good Example? Modeling Exemplar Selection with Neural Network Representations

Department of Psychology, University of Southern California(心理学系,南加州大学);Department of Statistics and Data Science, University of California, Los Angeles(统计与数据科学系,加州大学洛杉矶分校)

Fanxiao Wani Qiu, Oscar Leong, Alexander LaTourrette

AI总结:

本文通过神经网络表示和原则性子集选择标准建模人类实例选择,发现联合代表性与多样性结合的策略最能反映人类判断,且转换器表示比卷积网络更符合人类行为。

摘要:

教学需要将丰富的类别分布浓缩成一小组有信息的例子。尽管先前的研究表明,人类在教学时考虑了代表性和多样性,但这些权衡背后的基本计算原理仍不清楚。我们通过使用神经网络特征表示和原则性的子集选择标准来建模人类实例选择来填补这一空白。新的视觉类别沿一维形态连续体嵌入,使用预训练的视觉模型,并且选择策略在强调原型性、联合代表性和多样性方面有所不同。成年参与者选择一到三个例子来教一个学习者。模型-人类比较表明,基于联合代表性或其与多样性的结合的策略最好地捕捉了人类判断,而纯原型性或多样性策略表现较差。此外,基于转换器的表示 consistently 更紧密地与人类行为一致,比卷积网络更一致。这些结果突显了数据集蒸馏方法在机器学习中的潜在用途作为教学的计算模型。

英文摘要:

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.

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。

↑