Stream-Based Active Learning with Cooperative Neural Networks for Data-Efficient Partial Inverse Design: An Automotive Glass Run Channel Case Study

2026-10-07

AI Summary

This study addresses the challenge of scarce labeled data in engineering inverse design, where high simulation costs hinder the efficient inference of missing design variables. To overcome this limitation, we propose CoNN-AL, a framework that integrates collaborative neural networks, denoising autoencoders, and streaming active learning. By leveraging Monte Carlo Dropout for uncertainty quantification, the approach enables real-time selection and annotation of high-value samples. Evaluated on an automotive glass dataset comprising 900,000 samples, CoNN-AL achieves an R² exceeding 0.967 using only 2.3% of the labels, reducing annotation requirements by 30%–40% compared to random sampling. Furthermore, we publicly release this large-scale dataset to facilitate future research in data-efficient inverse design.

Abstract

Inverse design in engineering often runs into a simple problem. Each labeled training sample must be produced through expensive simulation, so building a large dataset is slow and costly. This study addresses that problem for partial inverse design, where only some design variables are specified and the rest must be inferred to reach a target performance value. We propose CoNN-AL, a framework for data-efficient partial inverse design that adds stream-based active learning to the Cooperative Neural Network with Denoising Autoencoder (CoNN-DAE). The model estimates predictive uncertainty through Monte Carlo dropout and uses it to decide, in real time, which incoming candidate samples are worth labeling, so the limited labeling budget is spent on the most informative designs. We validate the framework on a real-world automotive glass run channel dataset of more than 900,000 unique simulated designs. With only 20,000 actively selected labels, about 2.3% of the training pool, CoNN-AL reaches R-squared values of 0.967 to 0.982 across all missing-variable levels, approaching the upper-bound models trained on far more data. It reaches R-squared of at least 0.95 with 30 to 40% fewer labels than random sampling at the more difficult missing-variable levels and, at the most challenging level, is the only strategy in this study to reach R-squared of 0.98. Together with this work, we publicly release the dataset to support future research on data-driven design.

Innovation

• Active Learning
• Inverse Design
• Cooperative Neural Networks
• Monte Carlo Dropout
• Denoising Autoencoder