VIRL: Volume-Informed Representation Learning towards Few-shot Manufacturability Estimation

TL;DR

VIRL introduces a volume-informed pre-training approach for 3D geometric encoders, significantly improving few-shot manufacturability estimation across multiple indicators with limited data, and explores efficient deployment strategies like LoRA and normalization techniques.

Contribution

The paper presents VIRL, a novel volume-informed pre-training method for 3D geometric encoders, enhancing few-shot manufacturability prediction and analyzing deployment strategies such as LoRA and normalization.

Findings

VIRL pre-training improves generalizability with limited data.

LoRA achieves stable performance with less computational cost.

Static normalization performs consistently well across tasks.

Abstract

Designing for manufacturing poses significant challenges in part due to the computation bottleneck of Computer-Aided Manufacturing (CAM) simulations. Although deep learning as an alternative offers fast inference, its performance is dependently bounded by the need for abundant training data. Representation learning, particularly through pre-training, offers promise for few-shot learning, aiding in manufacturability tasks where data can be limited. This work introduces VIRL, a Volume-Informed Representation Learning approach to pre-train a 3D geometric encoder. The pretrained model is evaluated across four manufacturability indicators obtained from CAM simulations: subtractive machining (SM) time, additive manufacturing (AM) time, residual von Mises stress, and blade collisions during Laser Power Bed Fusion process. Across all case studies, the model pre-trained by VIRL shows substantial enhancements on demonstrating improved generalizability with limited data and superior performance with larger datasets. Regarding deployment strategy, case-specific phenomenon exists where finetuning VIRL-pretrained models adversely affects AM tasks with limited data but benefits SM time prediction. Moreover, the efficacy of Low-rank adaptation (LoRA), which balances between probing and finetuning, is explored. LoRA shows stable performance akin to probing with limited data, while achieving a higher upper bound than probing as data size increases, without the computational costs of finetuning. Furthermore, static normalization of manufacturing indicators consistently performs well across tasks, while dynamic normalization enhances performance when a reliable task dependent input is available.