Matches in SemOpenAlex for { <https://semopenalex.org/work/W3036157773> ?p ?o ?g. }
- W3036157773 abstract "One of the main challenges in using deep learning-based methods for simulating physical systems and solving partial differential equations (PDEs) is formulating physics-based data in the desired structure for neural networks. Graph neural networks (GNNs) have gained popularity in this area since graphs offer a natural way of modeling particle interactions and provide a clear way of discretizing the continuum models. However, the graphs constructed for approximating such tasks usually ignore long-range interactions due to unfavorable scaling of the computational complexity with respect to the number of nodes. The errors due to these approximations scale with the discretization of the system, thereby not allowing for generalization under mesh-refinement. Inspired by the classical multipole methods, we propose a novel multi-level graph neural network framework that captures interaction at all ranges with only linear complexity. Our multi-level formulation is equivalent to recursively adding inducing points to the kernel matrix, unifying GNNs with multi-resolution matrix factorization of the kernel. Experiments confirm our multi-graph network learns discretization-invariant solution operators to PDEs and can be evaluated in linear time." @default.
- W3036157773 created "2020-06-25" @default.
- W3036157773 creator A5014498545 @default.
- W3036157773 creator A5025458230 @default.
- W3036157773 creator A5032114852 @default.
- W3036157773 creator A5038884528 @default.
- W3036157773 creator A5052016306 @default.
- W3036157773 creator A5052584123 @default.
- W3036157773 creator A5074720524 @default.
- W3036157773 date "2020-06-16" @default.
- W3036157773 modified "2023-09-27" @default.
- W3036157773 title "Multipole Graph Neural Operator for Parametric Partial Differential Equations." @default.
- W3036157773 cites W1901129140 @default.
- W3036157773 cites W1998646770 @default.
- W3036157773 cites W2038524628 @default.
- W3036157773 cites W2052690618 @default.
- W3036157773 cites W2110126483 @default.
- W3036157773 cites W2117926105 @default.
- W3036157773 cites W2132820941 @default.
- W3036157773 cites W2295099209 @default.
- W3036157773 cites W2515505748 @default.
- W3036157773 cites W2519887557 @default.
- W3036157773 cites W2606780347 @default.
- W3036157773 cites W2624431344 @default.
- W3036157773 cites W2736092219 @default.
- W3036157773 cites W2760972773 @default.
- W3036157773 cites W2766453196 @default.
- W3036157773 cites W2784733489 @default.
- W3036157773 cites W2789186812 @default.
- W3036157773 cites W2805516822 @default.
- W3036157773 cites W2885076212 @default.
- W3036157773 cites W2899038170 @default.
- W3036157773 cites W2899283552 @default.
- W3036157773 cites W2914520121 @default.
- W3036157773 cites W2918342466 @default.
- W3036157773 cites W2939129005 @default.
- W3036157773 cites W2942681667 @default.
- W3036157773 cites W2952832237 @default.
- W3036157773 cites W2962867885 @default.
- W3036157773 cites W2963149188 @default.
- W3036157773 cites W2963504959 @default.
- W3036157773 cites W2963798430 @default.
- W3036157773 cites W2964159024 @default.
- W3036157773 cites W2989600087 @default.
- W3036157773 cites W2996324165 @default.
- W3036157773 cites W3010501116 @default.
- W3036157773 cites W3011182352 @default.
- W3036157773 cites W3011767095 @default.
- W3036157773 cites W3015062287 @default.
- W3036157773 cites W3021053516 @default.
- W3036157773 cites W3021748939 @default.
- W3036157773 cites W3028316595 @default.
- W3036157773 cites W3101765447 @default.
- W3036157773 cites W3123883114 @default.
- W3036157773 cites W626074782 @default.
- W3036157773 cites W8052360 @default.
- W3036157773 hasPublicationYear "2020" @default.
- W3036157773 type Work @default.
- W3036157773 sameAs 3036157773 @default.
- W3036157773 citedByCount "12" @default.
- W3036157773 countsByYear W30361577732020 @default.
- W3036157773 countsByYear W30361577732021 @default.
- W3036157773 crossrefType "posted-content" @default.
- W3036157773 hasAuthorship W3036157773A5014498545 @default.
- W3036157773 hasAuthorship W3036157773A5025458230 @default.
- W3036157773 hasAuthorship W3036157773A5032114852 @default.
- W3036157773 hasAuthorship W3036157773A5038884528 @default.
- W3036157773 hasAuthorship W3036157773A5052016306 @default.
- W3036157773 hasAuthorship W3036157773A5052584123 @default.
- W3036157773 hasAuthorship W3036157773A5074720524 @default.
- W3036157773 hasConcept C11413529 @default.
- W3036157773 hasConcept C121332964 @default.
- W3036157773 hasConcept C126255220 @default.
- W3036157773 hasConcept C134306372 @default.
- W3036157773 hasConcept C135115559 @default.
- W3036157773 hasConcept C154945302 @default.
- W3036157773 hasConcept C28826006 @default.
- W3036157773 hasConcept C33923547 @default.
- W3036157773 hasConcept C41008148 @default.
- W3036157773 hasConcept C50644808 @default.
- W3036157773 hasConcept C52765159 @default.
- W3036157773 hasConcept C62520636 @default.
- W3036157773 hasConcept C73000952 @default.
- W3036157773 hasConcept C80444323 @default.
- W3036157773 hasConcept C93779851 @default.
- W3036157773 hasConceptScore W3036157773C11413529 @default.
- W3036157773 hasConceptScore W3036157773C121332964 @default.
- W3036157773 hasConceptScore W3036157773C126255220 @default.
- W3036157773 hasConceptScore W3036157773C134306372 @default.
- W3036157773 hasConceptScore W3036157773C135115559 @default.
- W3036157773 hasConceptScore W3036157773C154945302 @default.
- W3036157773 hasConceptScore W3036157773C28826006 @default.
- W3036157773 hasConceptScore W3036157773C33923547 @default.
- W3036157773 hasConceptScore W3036157773C41008148 @default.
- W3036157773 hasConceptScore W3036157773C50644808 @default.
- W3036157773 hasConceptScore W3036157773C52765159 @default.
- W3036157773 hasConceptScore W3036157773C62520636 @default.
- W3036157773 hasConceptScore W3036157773C73000952 @default.
- W3036157773 hasConceptScore W3036157773C80444323 @default.
- W3036157773 hasConceptScore W3036157773C93779851 @default.