Evaluating Designer Learning and Performance in Interactive Deep Generative Design

Deep generative models have shown significant promise in improving performance in design space exploration. But there is limited understanding of their interpretability, a necessity when model explanations are desired and problems are ill-defined. Interpretability involves learning design features behind design performance, called designer learning. This study explores human–machine collaboration’s effects on designer learning and design performance. We conduct an experiment (N = 42) designing mechanical metamaterials using a conditional variational autoencoder. The independent variables are: (i) the level of automation of design synthesis, e.g., manual (where the user manually manipulates design variables), manual feature-based (where the user manipulates the weights of the features learned by the encoder), and semi-automated feature-based (where the agent generates a local design based on a start design and user-selected step size); and (ii) feature semanticity, e.g., meaningful versus abstract features. We assess feature-specific learning using item response theory and design performance using utopia distance and hypervolume improvement. The results suggest that design performance depends on the subjects’ feature-specific knowledge, emphasizing the precursory role of learning. The semi-automated synthesis locally improves the utopia distance. Still, it does not result in higher global hypervolume improvement compared to manual design synthesis and reduced designer learning compared to manual feature-based synthesis. The subjects learn semantic features better than abstract features only when design performance is sensitive to them. Potential cognitive constructs influencing learning in human–machine collaborative settings are discussed, such as cognitive load and recognition heuristics.