Function+Data Flow: A Framework to Specify Machine Learning Pipelines for Digital Twinning

• URL: http://arxiv.org/abs/2406.19670v2
• Date: Mon, 8 Jul 2024 08:28:34 GMT
• Title: Function+Data Flow: A Framework to Specify Machine Learning Pipelines for Digital Twinning
• Abstract summary: Digital twins (DTs) for physical systems increasingly leverage artificial intelligence (AI) Here we propose a domain-specific language (t+Data Flow) to describe AI pipelines within DTs. Specifically, t treats functions as first-class citizens, enabling effective manipulation of models learned with AI.
• Score: 2.27626288527213
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The development of digital twins (DTs) for physical systems increasingly leverages artificial intelligence (AI), particularly for combining data from different sources or for creating computationally efficient, reduced-dimension models. Indeed, even in very different application domains, twinning employs common techniques such as model order reduction and modelization with hybrid data (that is, data sourced from both physics-based models and sensors). Despite this apparent generality, current development practices are ad-hoc, making the design of AI pipelines for digital twinning complex and time-consuming. Here we propose Function+Data Flow (FDF), a domain-specific language (DSL) to describe AI pipelines within DTs. FDF aims to facilitate the design and validation of digital twins. Specifically, FDF treats functions as first-class citizens, enabling effective manipulation of models learned with AI. We illustrate the benefits of FDF on two concrete use cases from different domains: predicting the plastic strain of a structure and modeling the electromagnetic behavior of a bearing.

Related papers

• Building real-time digital twin instances with Function+Data Flow: user evaluation and extension for iterative pipelines [3.005601357270487]
  Digital twins (DTs) increasingly leverage artificial intelligence (AI) and machine learning (ML) pipelines to build real-time DTs from simulations and to instantiate them with historical data.<n>However, engineering these pipelines remains largely ad-hoc: pipelines are hard to specify, validate, and reuse, with scarce dedicated tooling.<n>Data Flow addresses this by defining a visual-specific language ( Function+ Function) that represents functions (ML models) explicitly, enabling their composition and reuse.
  arXiv  Detail & Related papers  (2026-08-19T03:12:38Z)
• Future Optical Flow Prediction Improves Robot Control & Video Generation [100.87884718953099]
  We introduce FOFPred, a novel optical flow forecasting model featuring a unified Vision-Language Model (VLM) and Diffusion architecture.<n>Our model is trained on web-scale human activity data-a highly scalable but unstructured source.<n> Evaluations across robotic manipulation and video generation under language-driven settings establish the cross-domain versatility of FOFPred.
  arXiv  Detail & Related papers  (2026-01-15T18:49:48Z)
• URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model [76.08429266631823]
  We propose an end-to-end automatic reconstruction framework based on a 3D multimodal large language model (MLLM)<n>URDF-Anything utilizes an autoregressive prediction framework based on point-cloud and text multimodal input to jointly optimize geometric segmentation and kinematic parameter prediction.<n> Experiments on both simulated and real-world datasets demonstrate that our method significantly outperforms existing approaches.
  arXiv  Detail & Related papers  (2025-11-02T13:45:51Z)
• A Streaming Sparse Cholesky Method for Derivative-Informed Gaussian Process Surrogates Within Digital Twin Applications [13.47464152775253]
  Digital twins are developed to model the behavior of a specific physical asset (or twin)<n>They can consist of high-fidelity physics-based models or surrogates.<n>To adapt to a specific physical twin, the digital twin model must be updated using in-service data from that physical twin.
  arXiv  Detail & Related papers  (2025-11-01T02:20:28Z)
• High-Fidelity Digital Twins for Bridging the Sim2Real Gap in LiDAR-Based ITS Perception [3.1508266388327324]
  This paper proposes a high-fidelity digital twin (HiFi DT) framework that incorporates real-world background geometry, lane-level road topology, and sensor-specific specifications and placement.<n>Experiments show that the DT-trained model outperforms the equivalent model trained on real data by 4.8%.
  arXiv  Detail & Related papers  (2025-09-03T00:12:58Z)
• Coordinate In and Value Out: Training Flow Transformers in Ambient Space [6.911507447184487]
  Ambient Space Flow Transformers (ASFT) is a domain-agnostic approach to learn flow matching transformers in ambient space. We introduce a conditionally independent point-wise training objective that enables ASFT to make predictions continuously in coordinate space.
  arXiv  Detail & Related papers  (2024-12-05T01:00:07Z)
• Automatically Learning Hybrid Digital Twins of Dynamical Systems [56.69628749813084]
  Digital Twins (DTs) simulate the states and temporal dynamics of real-world systems. DTs often struggle to generalize to unseen conditions in data-scarce settings. In this paper, we propose an evolutionary algorithm ($textbfHDTwinGen$) to autonomously propose, evaluate, and optimize HDTwins.
  arXiv  Detail & Related papers  (2024-10-31T07:28:22Z)
• Automatic AI Model Selection for Wireless Systems: Online Learning via Digital Twinning [50.332027356848094]
  AI-based applications are deployed at intelligent controllers to carry out functionalities like scheduling or power control. The mapping between context and AI model parameters is ideally done in a zero-shot fashion. This paper introduces a general methodology for the online optimization of AMS mappings.
  arXiv  Detail & Related papers  (2024-06-22T11:17:50Z)
• FMint: Bridging Human Designed and Data Pretrained Models for Differential Equation Foundation Model [5.748690310135373]
  We propose a novel multi-modal foundation model, named textbfFMint, to bridge the gap between human-designed and data-driven models. Built on a decoder-only transformer architecture with in-context learning, FMint utilizes both numerical and textual data to learn a universal error correction scheme. Our results demonstrate the effectiveness of the proposed model in terms of both accuracy and efficiency compared to classical numerical solvers.
  arXiv  Detail & Related papers  (2024-04-23T02:36:47Z)
• Training Deep Surrogate Models with Large Scale Online Learning [48.7576911714538]
  Deep learning algorithms have emerged as a viable alternative for obtaining fast solutions for PDEs. Models are usually trained on synthetic data generated by solvers, stored on disk and read back for training. It proposes an open source online training framework for deep surrogate models.
  arXiv  Detail & Related papers  (2023-06-28T12:02:27Z)
• Enhanced multi-fidelity modelling for digital twin and uncertainty quantification [0.0]
  Data-driven models play a crucial role in digital twins, enabling real-time updates and predictions. The fidelity of available data and the scarcity of accurate sensor data often hinder the efficient learning of surrogate models. We propose a novel framework that begins by developing a robust multi-fidelity surrogate model.
  arXiv  Detail & Related papers  (2023-06-26T05:58:17Z)
• DINOv2: Learning Robust Visual Features without Supervision [75.42921276202522]
  This work shows that existing pretraining methods, especially self-supervised methods, can produce such features if trained on enough curated data from diverse sources. Most of the technical contributions aim at accelerating and stabilizing the training at scale. In terms of data, we propose an automatic pipeline to build a dedicated, diverse, and curated image dataset instead of uncurated data, as typically done in the self-supervised literature.
  arXiv  Detail & Related papers  (2023-04-14T15:12:19Z)
• Advancing Reacting Flow Simulations with Data-Driven Models [50.9598607067535]
  Key to effective use of machine learning tools in multi-physics problems is to couple them to physical and computer models. The present chapter reviews some of the open opportunities for the application of data-driven reduced-order modeling of combustion systems.
  arXiv  Detail & Related papers  (2022-09-05T16:48:34Z)
• Model-Based Deep Learning [155.063817656602]
  Signal processing, communications, and control have traditionally relied on classical statistical modeling techniques. Deep neural networks (DNNs) use generic architectures which learn to operate from data, and demonstrate excellent performance. We are interested in hybrid techniques that combine principled mathematical models with data-driven systems to benefit from the advantages of both approaches.
  arXiv  Detail & Related papers  (2020-12-15T16:29:49Z)
• Federated Knowledge Distillation [42.87991207898215]
  Federated distillation (FD) is a distributed learning solution that only exchanges the model outputs whose dimensions are commonly much smaller than the model sizes. This chapter provides a deep understanding of FD while demonstrating its communication efficiency and applicability to a variety of tasks. The second part elaborates on a baseline implementation of FD for a classification task, and illustrates its performance in terms of accuracy and communication efficiency compared to FL. The third part presents two selected applications, namely FD over asymmetric uplink-and-downlink wireless channels and FD for reinforcement learning.
  arXiv  Detail & Related papers  (2020-11-04T15:56:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.