Few-shot learning-based generative design of metamaterials with zero Poisson's ratio

Metamaterials with a zero Poisson's ratio offer significant advantages in robotic actuation and space exploration due to their precise control of deformation. However, existing machine learning techniques cannot be directly used to accelerate the design of such materials due to the scarcity of this property. We propose a few-shot learning-based framework to generate non-periodic metamaterials with zero Poisson's ratio. Our framework incorporates an out-of-distribution (OOD) target-oriented sampler into a conditional variational autoencoder (cVAE). Unlike other metamaterial generative models that only deal with continuous pixel data, our approach can handle discrete unit cell patterns by computing their probability distributions. We found that controlling the learning focus during the training process can effectively mitigate the scarcity of acceptable data within the training set. This mitigation is achieved by repeatedly selecting target samples through the OOD target-oriented sampler. Incorporating active learning into the training process can further enhance model efficiency by adaptively adjusting the ratio between acceptable and unacceptable samples. The impacts of training data size, effective data composition, and the number of iterations in active learning on design efficiency are discussed in detail. Compared to random trial-and-error generation, our model demonstrates a substantial increase in the acceptable rate, from 0.3 % to 39 %.