Neural networks often learn task-specific latent representations that fail to generalize to novel settings or tasks. Conversely, humans learn discrete representations (i.e., concepts or words) at a variety of abstraction levels (e.g., "bird" vs. "sparrow") and deploy the appropriate abstraction based on task. Inspired by this, we train neural models to generate a spectrum of discrete representations, and control the complexity of the representations (roughly, how many bits are allocated for encoding inputs) by tuning the entropy of the distribution over representations. In finetuning experiments, using only a small number of labeled examples for a new task, we show that (1) tuning the representation to a task-appropriate complexity level supports the highest finetuning performance, and (2) in a human-participant study, users were able to identify the appropriate complexity level for a downstream task using visualizations of discrete representations. Our results indicate a promising direction for rapid model finetuning by leveraging human insight.

翻译：神经网络常常学习到特定任务的潜在表征，这些表征难以泛化到新的环境或任务中。相比之下，人类能够学习不同抽象层次（如“鸟”与“麻雀”）的离散表征（即概念或词语），并根据任务需求选择合适的抽象层次。受此启发，我们训练神经网络模型生成一系列离散表征，并通过调整表征分布的熵来控制表征的复杂度（大致而言，即分配用于编码输入的比特数）。在微调实验中，仅使用少量新任务的标注样本，我们发现：（1）将表征调整到与任务匹配的复杂度水平可实现最高的微调性能；（2）在人类参与者研究中，用户能够通过离散表征的可视化识别出适合下游任务的复杂度水平。我们的研究结果表明，通过利用人类洞察力实现快速模型微调是一个有前景的方向。