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：神经网络常学习任务特定的潜在表示，难以泛化到新场景或任务。相反，人类能够在多种抽象层级（如“鸟”与“麻雀”）上学习离散表示（即概念或词语），并根据任务部署合适的抽象层级。受此启发，我们训练神经模型生成一系列离散表示，并通过调整表示分布的熵来控制表示复杂度（大致指编码输入所分配的比特数）。在微调实验中，仅使用新任务的少量标注样本，我们发现：(1) 将表示调至任务适配的复杂度水平可达到最高微调性能；(2) 在人类参与者研究中，用户能通过离散表示的可视化识别下游任务的合适复杂度水平。我们的结果表明，通过利用人类洞察实现模型快速微调具有广阔前景。