تقرير
Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learning
| العنوان: | Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learning |
|---|---|
| المؤلفون: | Chen, Wuyang, Song, Jialin, Ren, Pu, Subramanian, Shashank, Morozov, Dmitriy, Mahoney, Michael W. |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science Statistics |
| مصطلحات موضوعية: | Computer Science - Machine Learning, Statistics - Machine Learning |
| الوصف: | Recent years have witnessed the promise of coupling machine learning methods and physical domainspecific insights for solving scientific problems based on partial differential equations (PDEs). However, being data-intensive, these methods still require a large amount of PDE data. This reintroduces the need for expensive numerical PDE solutions, partially undermining the original goal of avoiding these expensive simulations. In this work, seeking data efficiency, we design unsupervised pretraining for PDE operator learning. To reduce the need for training data with heavy simulation costs, we mine unlabeled PDE data without simulated solutions, and pretrain neural operators with physics-inspired reconstruction-based proxy tasks. To improve out-of-distribution performance, we further assist neural operators in flexibly leveraging in-context learning methods, without incurring extra training costs or designs. Extensive empirical evaluations on a diverse set of PDEs demonstrate that our method is highly data-efficient, more generalizable, and even outperforms conventional vision-pretrained models. |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2402.15734 |
| رقم الأكسشن: | edsarx.2402.15734 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |