English
Related papers

Related papers: NOFE - Neural Operator Function Embedding

200 papers

Stochastic differential equations (SDEs) and stochastic partial differential equations (SPDEs) are fundamental for modeling stochastic dynamics across the natural sciences and modern machine learning. Learning their solution operators with…

Machine Learning · Computer Science 2026-01-30 Dai Shi , Lequan Lin , Andi Han , Luke Thompson , José Miguel Hernández-Lobato , Zhiyong Wang , Junbin Gao

Node embedding is the task of extracting informative and descriptive features over the nodes of a graph. The importance of node embeddings for graph analytics, as well as learning tasks such as node classification, link prediction and…

Machine Learning · Computer Science 2019-06-17 Dimitris Berberidis , Georgios B. Giannakis

Deep learning surrogate models have shown promise in solving partial differential equations (PDEs). Among them, the Fourier neural operator (FNO) achieves good accuracy, and is significantly faster compared to numerical solvers, on a…

Machine Learning · Computer Science 2024-05-03 Zongyi Li , Daniel Zhengyu Huang , Burigede Liu , Anima Anandkumar

Neural operators extend data-driven models to map between infinite-dimensional functional spaces. These models have successfully solved continuous dynamical systems represented by differential equations, viz weather forecasting, fluid flow,…

Machine Learning · Computer Science 2023-10-13 Karn Tiwari , N M Anoop Krishnan , Prathosh A P

Graph-based learning is a cornerstone for analyzing structured data, with node classification as a central task. However, in many real-world graphs, nodes lack informative feature vectors, leaving only neighborhood connectivity and class…

Machine Learning · Computer Science 2025-10-14 Sujan Chakraborty , Rahul Bordoloi , Anindya Sengupta , Olaf Wolkenhauer , Saptarshi Bej

Function fitting/approximation plays a fundamental role in computer graphics and other engineering applications. While recent advances have explored neural networks to address this task, these methods often rely on architectures with many…

Graphics · Computer Science 2025-05-28 Biao Zhang , Peter Wonka

Neural Ordinary Differential Equations (NODEs) are a novel neural architecture, built around initial value problems with learned dynamics which are solved during inference. Thought to be inherently more robust against adversarial…

Machine Learning · Computer Science 2023-03-10 Mustafa Zeqiri , Mark Niklas Müller , Marc Fischer , Martin Vechev

As a primitive 3D data representation, point clouds are prevailing in 3D sensing, yet short of intrinsic structural information of the underlying objects. Such discrepancy poses great challenges on directly establishing correspondences…

Computer Vision and Pattern Recognition · Computer Science 2023-03-03 Puhua Jiang , Mingze Sun , Ruqi Huang

Neural operator models for solving partial differential equations (PDEs) often rely on global mixing mechanisms-such as spectral convolutions or attention-which tend to oversmooth sharp local dynamics and introduce high computational cost.…

Machine Learning · Computer Science 2025-10-01 Chun-Wun Cheng , Bin Dong , Carola-Bibiane Schönlieb , Angelica I Aviles-Rivero

Federated learning (FL) has rapidly evolved as a promising paradigm that enables collaborative model training across distributed participants without exchanging their local data. Despite its broad applications in fields such as computer…

Machine Learning · Computer Science 2024-10-15 Ziwei Li , Xiaoqi Wang , Hong-You Chen , Han-Wei Shen , Wei-Lun Chao

Rotary Positional Embedding (RoPE) is a common choice in transformer architectures for encoding relative positional information. Although earlier work has examined omitting RoPE in specific layers, the effect of varying the fraction of…

Machine Learning · Computer Science 2026-03-13 Mohammad Aflah Khan , Krishna P. Gummadi , Manish Gupta , Abhilasha Ravichander

We present $\phi-$DeepONet, a physics-informed neural operator designed to learn mappings between function spaces that may contain discontinuities or exhibit non-smooth behavior. Classical neural operators are based on the universal…

Computational Engineering, Finance, and Science · Computer Science 2026-04-10 Sumanta Roy , Stephen T. Castonguay , Pratanu Roy , Michael D. Shields

Neural operator surrogates for time-dependent partial differential equations (PDEs) conventionally employ autoregressive prediction schemes, which accumulate error over long rollouts and require uniform temporal discretization. We introduce…

Machine Learning · Computer Science 2025-12-08 Xianglong Hou , Xinquan Huang , Paris Perdikaris

We present a computational technique for modeling the evolution of dynamical systems in a reduced basis, with a focus on the challenging problem of modeling partially-observed partial differential equations (PDEs) on high-dimensional…

Machine Learning · Statistics 2024-12-25 Victor Churchill

Recent developments in mechanical, aerospace, and structural engineering have driven a growing need for efficient ways to model and analyse structures at much larger and more complex scales than before. While established numerical methods…

Machine Learning · Computer Science 2025-07-29 Rui Wu , Nikola Kovachki , Burigede Liu

Neural Ordinary Differential Equations (NODEs) often struggle to adapt to new dynamic behaviors caused by parameter changes in the underlying physical system, even when these dynamics are similar to previously observed behaviors. This…

Machine Learning · Computer Science 2025-09-30 Roussel Desmond Nzoyem , David A. W. Barton , Tom Deakin

We introduce sparse autoencoder neural operators (SAE-NOs), a new class of sparse autoencoders that operate in function spaces rather than fixed-dimensional Euclidean representations. We formalize the functional representation hypothesis,…

Machine Learning · Computer Science 2026-05-11 Bahareh Tolooshams , Ailsa Shen , Anima Anandkumar

Neural PDE solvers are increasingly used as learned surrogates for families of partial differential equations, where the key machine learning challenge is not only interpolation on a fixed benchmark distribution but generalization under…

Machine Learning · Computer Science 2026-05-26 Lennon Shikhman

Effective feature representation is key to the predictive performance of any algorithm. This paper introduces a meta-procedure, called Non-Euclidean Upgrading (NEU), which learns feature maps that are expressive enough to embed the…

Machine Learning · Statistics 2021-05-11 Anastasis Kratsios , Cody Hyndman

For identification of systems embedded in dynamic networks, applying the prediction error method (PEM) to a correct tailor-made parametrization of the complete network provided asymptotically efficient estimates. However, the network…

Systems and Control · Computer Science 2018-03-21 Miguel Galrinho , Riccardo Prota , Mina Ferizbegovic , Håkan Hjalmarsson