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
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.
Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars
Institute of Data Science, National University of Singapore(新加坡国立大学数据科学研究院);Dept. of Computer Science, National University of Singapore(新加坡国立大学计算机学院);LIDS and EECS, Massachusetts Institute of Technology(麻省理工学院LIDS与电子工程与计算机科学系);Guangdong Lab of AI and Digital Economy (SZ)(广东省人工智能与数字经济实验室(深圳))
From Selection to Scheduling: Federated Geometry-Aware Correction Makes Exemplar Replay Work Better under Continual Dynamic Heterogeneity
School of Software, Shandong University(山东大学软件学院);College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院);School of Computer Science and Technology, Harbin Institute of Technology(哈尔滨工业大学计算机科学与技术学院)
Dictionary Subselection Using an Overcomplete Joint Sparsity Model
Institute for Digital Communications (IDCom), The University of Edinburgh(爱丁堡大学数字通信研究所(IDCom));Paris Diderot University(巴黎第七大学);Institut Langevin(朗之万研究所)
Advancing Relation Extraction through Language Probing with Exemplars from Set Co-Expansion
Department of Computer Science, University of Illinois at Urbana-Champaign, USA(伊利诺伊大学厄巴纳-香槟分校计算机科学系);Linguistics Department, University of Illinois at Urbana-Champaign, USA(伊利诺伊大学厄巴纳-香槟分校语言学系)