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

• URL: http://arxiv.org/abs/2602.03144v1
• Date: Tue, 03 Feb 2026 05:57:02 GMT
• Title: What Makes a Good Example? Modeling Exemplar Selection with Neural Network Representations
• Authors: Fanxiao Wani Qiu, Oscar Leong, Alexander LaTourrette,
• Abstract summary: Teaching requires distilling a rich category distribution into a small set of informative exemplars.<n>Prior work shows that humans consider both representativeness and diversity when teaching.<n>We address this gap by modeling human exemplar selection using neural network feature representations and principled subset selection criteria.
• Score: 45.81163684522312
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Preview-based Category Contrastive Learning for Knowledge Distillation [53.551002781828146]
  We propose a novel preview-based category contrastive learning method for knowledge distillation (PCKD) It first distills the structural knowledge of both instance-level feature correspondence and the relation between instance features and category centers. It can explicitly optimize the category representation and explore the distinct correlation between representations of instances and categories.
  arXiv  Detail & Related papers  (2024-10-18T03:31:00Z)
• Learning Human-Aligned Representations with Contrastive Learning and Generative Similarity [9.63129238638334]
  Humans rely on effective representations to learn from few examples and abstract useful information from sensory data.<n>We use a Bayesian notion of generative similarity whereby two data points are considered similar if they are likely to have been sampled from the same distribution.<n>We demonstrate the utility of our approach by showing that it can be used to capture human-like representations of shape regularity, abstract Euclidean geometric concepts, and semantic hierarchies for natural images.
  arXiv  Detail & Related papers  (2024-05-29T18:01:58Z)
• A Probabilistic Model Behind Self-Supervised Learning [53.64989127914936]
  In self-supervised learning (SSL), representations are learned via an auxiliary task without annotated labels. We present a generative latent variable model for self-supervised learning. We show that several families of discriminative SSL, including contrastive methods, induce a comparable distribution over representations.
  arXiv  Detail & Related papers  (2024-02-02T13:31:17Z)
• Evaluating alignment between humans and neural network representations in image-based learning tasks [5.657101730705275]
  We tested how well the representations of $86$ pretrained neural network models mapped to human learning trajectories.<n>We found that while training dataset size was a core determinant of alignment with human choices, contrastive training with multi-modal data (text and imagery) was a common feature of currently publicly available models that predicted human generalisation.<n>In conclusion, pretrained neural networks can serve to extract representations for cognitive models, as they appear to capture some fundamental aspects of cognition that are transferable across tasks.
  arXiv  Detail & Related papers  (2023-06-15T08:18:29Z)
• Distinguishing representational geometries with controversial stimuli: Bayesian experimental design and its application to face dissimilarity judgments [0.5735035463793008]
  We show that a neural network trained to invert a 3D-face-model graphics is more human-aligned than the same architecture trained on identification, classification, or autoencoding. Our results indicate that a neural network trained to invert a 3D-face-model graphics is more human-aligned than the same architecture trained on identification, classification, or autoencoding.
  arXiv  Detail & Related papers  (2022-11-28T04:17:35Z)
• Human alignment of neural network representations [28.32452075196472]
  We investigate the factors that affect the alignment between the representations learned by neural networks and human mental representations inferred from behavioral responses.<n>We find that model scale and architecture have essentially no effect on the alignment with human behavioral responses.<n>We find that some human concepts such as food and animals are well-represented by neural networks whereas others such as royal or sports-related objects are not.
  arXiv  Detail & Related papers  (2022-11-02T15:23:16Z)
• Contrastive Learning for Fair Representations [50.95604482330149]
  Trained classification models can unintentionally lead to biased representations and predictions. Existing debiasing methods for classification models, such as adversarial training, are often expensive to train and difficult to optimise. We propose a method for mitigating bias by incorporating contrastive learning, in which instances sharing the same class label are encouraged to have similar representations.
  arXiv  Detail & Related papers  (2021-09-22T10:47:51Z)
• Semi-Supervised Few-Shot Classification with Deep Invertible Hybrid Models [4.189643331553922]
  We propose a deep invertible hybrid model which integrates discriminative and generative learning at a latent space level for semi-supervised few-shot classification. Our main originality lies in our integration of these components at a latent space level, which is effective in preventing overfitting.
  arXiv  Detail & Related papers  (2021-05-22T05:55:16Z)
• On the Transferability of Adversarial Attacksagainst Neural Text Classifier [121.6758865857686]
  We investigate the transferability of adversarial examples for text classification models. We propose a genetic algorithm to find an ensemble of models that can induce adversarial examples to fool almost all existing models. We derive word replacement rules that can be used for model diagnostics from these adversarial examples.
  arXiv  Detail & Related papers  (2020-11-17T10:45:05Z)
• Few-shot Classification via Adaptive Attention [93.06105498633492]
  We propose a novel few-shot learning method via optimizing and fast adapting the query sample representation based on very few reference samples. As demonstrated experimentally, the proposed model achieves state-of-the-art classification results on various benchmark few-shot classification and fine-grained recognition datasets.
  arXiv  Detail & Related papers  (2020-08-06T05:52:59Z)
• Similarity of Neural Networks with Gradients [8.804507286438781]
  We propose to leverage both feature vectors and gradient ones into designing the representation of a neural network. We show that the proposed approach provides a state-of-the-art method for computing similarity of neural networks.
  arXiv  Detail & Related papers  (2020-03-25T17:04:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.