الملخص
Large-scale pre-training has improved the generalization of neural operators across diverse PDEs. However, existing PDE foundation models still struggle with heterogeneous dynamics, where shared representations may cause knowledge interference, while mixture-of-experts (MoE) architectures suffer from increasing expert redundancy. We propose SPEAR, a spectral-disentangled MoE neural operator with knowledge-guided expert aggregation for large-scale PDE pre-training. SPEAR decouples latent features into low- and high-frequency components, enabling shared modeling of transferable dynamics and specialized learning of PDE-specific patterns. To address expert redundancy, we design a knowledge-guided expert aggregation strategy that measures expert similarity from dataset-specific learned knowledge and routing preferences, enabling the identification and consolidation of similar experts. Experiments on twelve PDE datasets and multiple downstream benchmarks demonstrate superior performance in pre-training, fine-tuning, and transfer learning. Furthermore, our aggregation strategy reduces the number of experts by 50\% while maintaining or improving prediction accuracy, achieving a balance between model efficiency and generalization for PDE foundation models.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Sun, D., Zhou, X., Wang, X., Lyu, W., Tang, J., & Luo, B. (2026). SPEAR: A Spectral-Disentangled MoE Neural Operator with Knowledge-Guided Expert Aggregation for Large-Scale PDE Pretraining. https://omanscience.com/ar/articles/spear-a-spectral-disentangled-moe-neural-operator-with-knowledge-guided-expert-aggregation-for-large-scale-pde-pretraining
MLA 9
Sun, Dengdi, et al. "SPEAR: A Spectral-Disentangled MoE Neural Operator with Knowledge-Guided Expert Aggregation for Large-Scale PDE Pretraining." https://omanscience.com/ar/articles/spear-a-spectral-disentangled-moe-neural-operator-with-knowledge-guided-expert-aggregation-for-large-scale-pde-pretraining.
شيكاغو (المؤلف–التاريخ)
Sun, Dengdi, Xiaoya Zhou, Xiao Wang, Wanli Lyu, Jin Tang, and Bin Luo. 2026. "SPEAR: A Spectral-Disentangled MoE Neural Operator with Knowledge-Guided Expert Aggregation for Large-Scale PDE Pretraining." https://omanscience.com/ar/articles/spear-a-spectral-disentangled-moe-neural-operator-with-knowledge-guided-expert-aggregation-for-large-scale-pde-pretraining.
هارفارد
Sun, D., Zhou, X., Wang, X., Lyu, W., Tang, J. and Luo, B. (2026) 'SPEAR: A Spectral-Disentangled MoE Neural Operator with Knowledge-Guided Expert Aggregation for Large-Scale PDE Pretraining', Available at: https://omanscience.com/ar/articles/spear-a-spectral-disentangled-moe-neural-operator-with-knowledge-guided-expert-aggregation-for-large-scale-pde-pretraining.
فانكوفر
Sun D, Zhou X, Wang X, Lyu W, Tang J, Luo B. SPEAR: A Spectral-Disentangled MoE Neural Operator with Knowledge-Guided Expert Aggregation for Large-Scale PDE Pretraining. https://omanscience.com/ar/articles/spear-a-spectral-disentangled-moe-neural-operator-with-knowledge-guided-expert-aggregation-for-large-scale-pde-pretraining
IEEE
D. Sun, X. Zhou, X. Wang, W. Lyu, J. Tang, and B. Luo, "SPEAR: A Spectral-Disentangled MoE Neural Operator with Knowledge-Guided Expert Aggregation for Large-Scale PDE Pretraining," https://omanscience.com/ar/articles/spear-a-spectral-disentangled-moe-neural-operator-with-knowledge-guided-expert-aggregation-for-large-scale-pde-pretraining.